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

    Neuronpedia

    INDEX
    Explanations

    references to winners or winning in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antar
    -0.17
    ers
    -0.17
    cir
    -0.16
    shed
    -0.15
    aille
    -0.15
    errick
    -0.15
    allon
    -0.14
    ez
    -0.14
    iero
    -0.14
    aber
    -0.14
    POSITIVE LOGITS
    hood
    0.17
    ãĤĩ
    0.16
    ãĤĥ
    0.15
    _undo
    0.15
    isia
    0.15
    inus
    0.15
    اث
    0.14
    nable
    0.14
    ichten
    0.14
    _fds
    0.14
    Act Density 0.024%

    No Known Activations