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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edIn
    -0.53
    regate
    -0.51
    ï
    -0.50
    Make
    -0.47
    inav
    -0.47
     Seym
    -0.46
    —-
    -0.46
    Ãĥ
    -0.46
    Leave
    -0.46
    dates
    -0.45
    POSITIVE LOGITS
     incapable
    0.71
     deprecated
    0.70
     unable
    0.69
     located
    0.67
     liable
    0.67
     forbidden
    0.66
     regarded
    0.65
     situated
    0.65
     honoured
    0.65
     able
    0.64
    Act Density 0.542%

    No Known Activations