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

    Neuronpedia

    INDEX
    Explanations

    phrases that include the word "for" indicating purpose or function

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Canaver
    -0.76
    antasy
    -0.71
    rend
    -0.68
    feature
    -0.68
     corrid
    -0.64
    vez
    -0.64
    aq
    -0.63
     coinc
    -0.62
    MY
    -0.61
    olicy
    -0.60
    POSITIVE LOGITS
     sale
    0.77
     adults
    0.74
     Adults
    0.71
     kids
    0.68
     hire
    0.66
     boys
    0.65
     elders
    0.63
     guitar
    0.63
     children
    0.62
    thood
    0.62
    Act Density 0.096%

    No Known Activations