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

    Neuronpedia

    INDEX
    Explanations

    commands typically associated with instructions or directives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    echan
    -0.15
     Gut
    -0.15
     Honest
    -0.15
    NSE
    -0.15
    coma
    -0.15
    usat
    -0.14
     Relay
    -0.14
    ì½ĺ
    -0.14
    oise
    -0.14
    bia
    -0.14
    POSITIVE LOGITS
    eldorf
    0.19
    etch
    0.16
    /umd
    0.16
     bes
    0.15
     Crowley
    0.14
     Epic
    0.14
    ughter
    0.14
    ichern
    0.14
    enco
    0.14
     paid
    0.13
    Act Density 0.017%

    No Known Activations