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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing strong emotions or attitudes

    oai_token-act-pair · gpt-3.5-turbo

    quotes and dialogue in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    İĭ
    -0.66
     Flavoring
    -0.62
    ²¾
    -0.59
    ¥
    -0.58
     Skydragon
    -0.58
    stantial
    -0.57
     mids
    -0.56
    rador
    -0.55
    aser
    -0.55
    estine
    -0.55
    POSITIVE LOGITS
    /"
    0.85
     advised
    0.72
     âĢķ
    0.71
     -
    0.71
     --
    0.69
    isSpecialOrderable
    0.69
     implies
    0.68
     —
    0.68
     trope
    0.68
     advises
    0.67
    Act Density 0.066%

    No Known Activations