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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating importance or necessity

    oai_token-act-pair · gpt-3.5-turbo

    the past tense form of the verb 'to be'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abilia
    -0.87
    isode
    -0.75
    DAQ
    -0.74
    Trend
    -0.72
    otyp
    -0.69
     Horton
    -0.69
    orthy
    -0.68
    STAR
    -0.67
     Hispanic
    -0.67
     Codex
    -0.65
    POSITIVE LOGITS
     watered
    0.82
    sed
    0.78
     climbs
    0.76
     moss
    0.73
     escal
    0.72
     shocks
    0.72
     paralysis
    0.70
     carrots
    0.69
     travers
    0.69
     slic
    0.69
    Act Density 0.000%

    No Known Activations