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

    Neuronpedia

    INDEX
    Explanations

    instances of specific legal citation formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ây
    -0.16
    gua
    -0.15
    izont
    -0.15
    ané
    -0.15
    sonian
    -0.15
    skyt
    -0.14
    ké
    -0.14
    aires
    -0.14
    curve
    -0.14
    edores
    -0.14
    POSITIVE LOGITS
    he
    0.34
     he
    0.29
    here
    0.28
    hat
    0.28
     wo
    0.25
    _he
    0.24
     hey
    0.24
     hat
    0.24
    .he
    0.24
    hey
    0.23
    Act Density 0.026%

    No Known Activations