Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions and phrases that indicate feelings and experiences related to personal perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows verbs like "sound", "find", "seems", or "is"

    np_acts-logits-general · gemini-2.0-flash

    sounds qualifying descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mediocrity
    -0.58
    <bos>
    -0.52
     criminality
    -0.52
    libft
    -0.51
     قرب
    -0.51
     pessimism
    -0.50
     regularity
    -0.50
     normality
    -0.49
     uintptr
    -0.49
     rationality
    -0.49
    POSITIVE LOGITS
     very
    0.82
     extremely
    0.82
     quite
    0.80
     both
    0.76
     JUGA
    0.70
     exceptionally
    0.70
     incredibly
    0.69
     thiệu
    0.69
     highly
    0.68
    extAlignment
    0.67
    Act Density 0.853%

    No Known Activations