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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate detailed explanations or descriptions of events or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    detailed descriptions or accounts of events

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    iferation
    -0.73
    assic
    -0.71
    AU
    -0.66
    stack
    -0.66
    think
    -0.65
    Desktop
    -0.63
    AppData
    -0.62
    lua
    -0.62
    achable
    -0.61
    atan
    -0.60
    POSITIVE LOGITS
     similarities
    0.82
     endorsements
    0.72
     how
    0.70
     parallels
    0.69
     links
    0.67
     excerpts
    0.66
     assass
    0.64
     aspects
    0.64
     harrowing
    0.63
     shortcomings
    0.62
    Act Density 0.280%

    No Known Activations