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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and their relationships to others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     himself
    -0.22
     Himself
    -0.18
    adius
    -0.18
     koji
    -0.17
     Jr
    -0.17
     Igor
    -0.16
    ichael
    -0.16
    Junior
    -0.15
     Kenneth
    -0.15
     jr
    -0.15
    POSITIVE LOGITS
    Ann
    0.32
    ann
    0.30
     Ann
    0.29
     herself
    0.27
    mae
    0.23
     anne
    0.22
    beth
    0.21
    _ann
    0.20
    Anne
    0.20
     Anne
    0.20
    Act Density 0.185%

    No Known Activations