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

    Neuronpedia

    INDEX
    Explanations

    statements questioning societal norms and responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tober
    -0.16
    alez
    -0.16
     окÑĢÑĥж
    -0.15
    )prepare
    -0.15
    &type
    -0.14
    ando
    -0.14
    &o
    -0.14
     Campos
    -0.14
    jamin
    -0.14
    ikes
    -0.14
    POSITIVE LOGITS
    aktu
    0.16
    antis
    0.16
    rack
    0.15
    åĦĢ
    0.15
    ç
    0.15
     according
    0.14
     upp
    0.14
    MLS
    0.14
    quine
    0.14
    ziel
    0.14
    Act Density 0.256%

    No Known Activations