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

    Neuronpedia

    INDEX
    Explanations

    phrases related to perceptions of reality and the significance of personal experiences

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

    Intensifiers modifying adjectives

    np_acts-logits-general · gemini-2.0-flash

    intensifiers and comparatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fjspx
    -0.55
     formality
    -0.54
    opsida
    -0.53
     confidentiality
    -0.52
     shenanigans
    -0.52
     Confidentiality
    -0.51
     antics
    -0.49
     professionalism
    -0.49
     étoit
    -0.49
     acidity
    -0.49
    POSITIVE LOGITS
     beautiful
    0.91
    تقاوى
    0.89
     alive
    0.73
    EDEFAULT
    0.70
    beautiful
    0.69
    \{\\
    0.68
    :✨
    0.66
     evil
    0.65
    jestic
    0.65
     sublime
    0.64
    Act Density 0.499%

    No Known Activations