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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty and curiosity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Datuak
    -0.57
    nologue
    -0.55
    djangoproject
    -0.54
    mandu
    -0.49
    人們
    -0.48
     NgModule
    -0.47
    bufio
    -0.45
    osd
    -0.45
    人们
    -0.45
     coque
    -0.44
    POSITIVE LOGITS
    发表于
    0.83
     myſelf
    0.72
     Ahnung
    0.72
    FTFY
    0.70
     ModelExpression
    0.67
    原始内容存档于
    0.67
     myself
    0.67
    öszi
    0.65
    Been
    0.61
     hâte
    0.60
    Act Density 0.302%

    No Known Activations