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

    Neuronpedia

    INDEX
    Explanations

    phrases related to isolating or separating things from a larger group

    oai_token-act-pair · gpt-3.5-turbo

    terms related to isolation and segregation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jriwal
    -0.81
    ember
    -0.80
    */(
    -0.70
    apan
    -0.69
    etheus
    -0.66
    yrus
    -0.66
    inez
    -0.65
    ocaust
    -0.64
    pmwiki
    -0.63
     Employees
    -0.63
    POSITIVE LOGITS
    olate
    0.89
     isolate
    0.77
    iven
    0.76
    oute
    0.73
    sym
    0.73
    ĨĴ
    0.71
    opsis
    0.68
    /+
    0.65
    qqa
    0.65
    knit
    0.65
    Act Density 0.030%

    No Known Activations