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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal preference and recommendations

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

    my favorite

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.48
    parsedMessage
    -0.45
    CharacterOffset
    -0.44
     مرئيه
    -0.43
    oneofs
    -0.42
     defStyleAttr
    -0.42
    ":[{
    -0.40
    rungsseite
    -0.39
    참고
    -0.38
    Still
    -0.38
    POSITIVE LOGITS
     new
    0.70
     favorite
    0.59
     henceforth
    0.57
     favourite
    0.56
     keeper
    0.55
    リピ
    0.55
     permanent
    0.54
     FAVORITE
    0.54
     favorites
    0.53
     nieuwe
    0.53
    Act Density 0.016%

    No Known Activations