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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ylon
    -0.15
    ged
    -0.15
    icens
    -0.15
    ise
    -0.14
    ä¸įäºĨ
    -0.14
    ores
    -0.14
    alse
    -0.14
    ван
    -0.14
    gis
    -0.14
    ule
    -0.13
    POSITIVE LOGITS
    /how
    0.30
     there
    0.20
     INCIDENT
    0.15
     it
    0.14
    Bias
    0.14
    olated
    0.14
    profits
    0.14
     Edwin
    0.13
     any
    0.13
     they
    0.13
    Act Density 0.022%

    No Known Activations