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

    Neuronpedia

    INDEX
    Explanations

    terms associated with creativity and relative comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ness
    -0.88
    nya
    -0.85
    ers
    -0.79
    r
    -0.78
    m
    -0.73
    n
    -0.71
    er
    -0.71
    iness
    -0.70
    nt
    -0.68
    z
    -0.65
    POSITIVE LOGITS
     ſeveral
    1.23
     Houſe
    1.21
     myſelf
    1.17
     Theſe
    1.09
     ―――――
    1.08
     houſe
    1.07
     pleaſure
    1.06
     themſelves
    1.04
     ſmall
    1.04
     Reſ
    1.03
    Act Density 0.273%

    No Known Activations