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

    Neuronpedia

    INDEX
    Explanations

    instances where the speaker is addressing or asking something of another person

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Byrne
    -0.15
    hazi
    -0.15
     Carbon
    -0.15
     carbon
    -0.15
    yla
    -0.14
    dera
    -0.14
    nze
    -0.14
    iset
    -0.14
    oston
    -0.14
    ining
    -0.14
    POSITIVE LOGITS
    çŃĴ
    0.14
    alic
    0.14
    Äįer
    0.14
    orie
    0.14
    oth
    0.14
    ortho
    0.14
    _male
    0.14
     Morr
    0.13
    .define
    0.13
    _USAGE
    0.13
    Act Density 0.018%

    No Known Activations