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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs ending in 'ed' and some 'ing' verbs

    oai_token-act-pair · gpt-3.5-turbo

    past tense verbs or actions that denote specific activities or achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    selves
    -0.77
    Higher
    -0.71
    respective
    -0.68
    members
    -0.67
    volent
    -0.66
    inning
    -0.66
    Compared
    -0.65
     selves
    -0.65
    board
    -0.64
    folk
    -0.63
    POSITIVE LOGITS
     himself
    0.83
     herself
    0.68
     his
    0.67
    isons
    0.60
     extensively
    0.60
     stern
    0.60
     unsuccessfully
    0.60
     Hitchcock
    0.59
     dism
    0.58
     showc
    0.58
    Act Density 0.471%

    No Known Activations