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

    Neuronpedia

    INDEX
    Explanations

    specific incidents or events

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific incident

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ularity
    -0.85
    emouth
    -0.81
    tsky
    -0.80
    icrobial
    -0.79
    ichick
    -0.78
    oliberal
    -0.75
    azy
    -0.74
    heit
    -0.73
    ophers
    -0.73
    rows
    -0.72
    POSITIVE LOGITS
     involving
    1.08
     perpetrated
    0.87
    uality
    0.83
     occurring
    0.81
     occurred
    0.81
     incident
    0.81
    uates
    0.81
     happened
    0.76
     incidents
    0.75
     unfolded
    0.74
    Act Density 0.048%

    No Known Activations