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

    Neuronpedia

    INDEX
    Explanations

    comparative terms and phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     referenties
    -0.80
     Rys
    -0.70
    ++);
    -0.68
     ་་
    -0.68
     Rais
    -0.67
     înal
    -0.67
     Patro
    -0.66
     GIP
    -0.65
     spleen
    -0.64
    ='".$
    -0.64
    POSITIVE LOGITS
     wie
    0.62
     yours
    0.61
    enumii
    0.59
    +#+
    0.59
     the
    0.58
     those
    0.57
     like
    0.55
    enumi
    0.54
     las
    0.53
     ours
    0.51
    Act Density 0.388%

    No Known Activations