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

    Neuronpedia

    INDEX
    Explanations

    mentions of team members within a group or organization

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or groups involved in a team or organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Scope
    -0.77
    BAT
    -0.72
    MER
    -0.71
    STAR
    -0.70
    anche
    -0.70
    PDATE
    -0.69
    okin
    -0.67
    aval
    -0.65
    asting
    -0.64
    obar
    -0.64
    POSITIVE LOGITS
    hips
    1.50
    ials
    0.84
    doms
    0.83
    bery
    0.81
    hea
    0.79
    hip
    0.79
    holders
    0.79
    ially
    0.78
    holder
    0.76
    ertodd
    0.74
    Act Density 0.080%

    No Known Activations