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

    Neuronpedia

    INDEX
    Explanations

    words associated with capable or functional qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ing
    -0.98
    n
    -0.95
    es
    -0.88
    N
    -0.81
    m
    -0.79
    ↵↵
    -0.77
    9
    -0.74
    T
    -0.73
    est
    -0.73
    th
    -0.73
    POSITIVE LOGITS
     Efq
    1.57
     myſelf
    1.52
     Jefus
    1.49
     Theſe
    1.44
    ^(@)
    1.42
     himſelf
    1.41
     ་་
    1.40
     ―――――
    1.39
     ſeveral
    1.37
     themſelves
    1.34
    Act Density 0.164%

    No Known Activations