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

    Neuronpedia

    INDEX
    Explanations

    verbs related to taking action or making something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "create" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     WATCHED
    -0.72
    phia
    -0.71
    duty
    -0.69
     Kro
    -0.67
    iere
    -0.66
     Adin
    -0.64
     Niet
    -0.63
     Gib
    -0.62
    cgi
    -0.62
     bour
    -0.61
    POSITIVE LOGITS
    女
    0.96
     havoc
    0.96
    idable
    0.88
    ãĥ¼ãĥĨãĤ£
    0.83
    Space
    0.80
    ãĥ©ãĥ³
    0.74
    gallery
    0.73
    unique
    0.73
    aldehyde
    0.71
    ãĥĨãĤ£
    0.71
    Act Density 0.070%

    No Known Activations