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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "type" or related terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "type" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivals
    -0.71
    =~=~
    -0.66
    ordial
    -0.66
    eming
    -0.61
    ellery
    -0.61
    negie
    -0.60
     disadvant
    -0.60
    emale
    -0.60
    rugged
    -0.57
     Admission
    -0.57
    POSITIVE LOGITS
     aloud
    1.06
    ahead
    0.90
    face
    0.84
     typing
    0.82
    faces
    0.78
    codes
    0.74
     alphabet
    0.73
     html
    0.72
     captcha
    0.72
     passwords
    0.72
    Act Density 0.041%

    No Known Activations