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

    Neuronpedia

    INDEX
    Explanations

    phrases related to origins or causes of events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating emergence or departure from a state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ļéĨĴ
    -0.87
    cious
    -0.76
    Export
    -0.72
    anooga
    -0.70
    EY
    -0.69
    ancial
    -0.65
    ingham
    -0.65
    uyomi
    -0.65
    Tips
    -0.63
     Illustrated
    -0.63
    POSITIVE LOGITS
    wards
    0.86
    fitted
    0.82
    stretched
    0.77
    doors
    0.75
    worn
    0.74
    flows
    0.73
    casts
    0.70
    doing
    0.70
    stri
    0.70
    breaks
    0.68
    Act Density 0.055%

    No Known Activations