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

    Neuronpedia

    INDEX
    Explanations

    phrases that express additional benefits or positive attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igo
    -0.17
    presso
    -0.16
    als
    -0.15
    declspec
    -0.15
    олоÑĪ
    -0.15
    -Token
    -0.14
    ë»
    -0.14
    ãĢģãĤĦ
    -0.13
    anel
    -0.13
    bj
    -0.13
    POSITIVE LOGITS
    enger
    0.17
    ieurs
    0.16
    ç£
    0.15
    adera
    0.14
    illa
    0.14
    ÑĶм
    0.14
    åĦ¿
    0.14
    .ng
    0.14
    ishing
    0.13
    EDA
    0.13
    Act Density 0.017%

    No Known Activations