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

    Neuronpedia

    INDEX
    Explanations

    structured arguments or discussions that lead to conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heed
    -0.17
    245
    -0.16
    845
    -0.16
     ho
    -0.15
    ono
    -0.14
     eros
    -0.14
     rum
    -0.14
    IGO
    -0.14
    565
    -0.14
     diver
    -0.13
    POSITIVE LOGITS
    ouston
    0.17
    licken
    0.15
    _RAM
    0.15
     collegiate
    0.15
    olla
    0.15
    criptor
    0.14
    isper
    0.14
    ÑĢеÑĤÑĮ
    0.14
    fsp
    0.14
     Colleg
    0.14
    Act Density 0.433%

    No Known Activations