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

    Neuronpedia

    INDEX
    Explanations

    verbs in the present tense

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "is."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stood
    -0.76
     Seym
    -0.72
     Chero
    -0.70
    accompan
    -0.69
    edIn
    -0.66
     sinks
    -0.65
     possessions
    -0.63
    Footnote
    -0.62
    ilaterally
    -0.61
     accompl
    -0.61
    POSITIVE LOGITS
    rael
    0.94
    senal
    0.82
    ometric
    0.73
    PORT
    0.73
     Psy
    0.70
    othermal
    0.69
    CRIPTION
    0.68
    olation
    0.67
    olate
    0.67
    ource
    0.65
    Act Density 0.049%

    No Known Activations