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

    Neuronpedia

    INDEX
    Explanations

    words related to forceful actions or transformations

    oai_token-act-pair · gpt-3.5-turbo

    words that end in the suffix 'ate' or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bang
    -0.72
    REL
    -0.72
    amar
    -0.70
    owitz
    -0.70
    azaki
    -0.69
    follow
    -0.66
    swick
    -0.66
    drawn
    -0.65
    backs
    -0.65
    é¾įå
    -0.63
    POSITIVE LOGITS
    urally
    0.74
     libel
    0.73
    ulate
    0.72
    mble
    0.72
    iate
    0.72
    ATING
    0.72
    ATED
    0.69
    ly
    0.68
    uate
    0.65
    aneously
    0.65
    Act Density 0.229%

    No Known Activations