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

    Neuronpedia

    INDEX
    Explanations

    statements related to choices and their consequences, especially in practical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é©
    -0.14
    irts
    -0.13
    rex
    -0.13
    kud
    -0.13
    ancies
    -0.13
    UA
    -0.13
    okt
    -0.13
    kb
    -0.12
    _aliases
    -0.12
    instr
    -0.12
    POSITIVE LOGITS
    erte
    0.17
    .vert
    0.14
    atta
    0.14
    avit
    0.14
    roe
    0.13
    ickey
    0.13
     ere
    0.13
    æħ§
    0.13
    otta
    0.13
     there
    0.13
    Act Density 0.205%

    No Known Activations