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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating correctness or suitability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isoft
    -0.16
     Bald
    -0.15
    deen
    -0.15
    iliz
    -0.14
    oris
    -0.14
     Beled
    -0.14
    éal
    -0.14
    _TYP
    -0.14
     Bucc
    -0.14
    icap
    -0.14
    POSITIVE LOGITS
    ilk
    0.17
    arch
    0.15
     Seal
    0.15
     choice
    0.14
     kind
    0.14
     refin
    0.14
     lies
    0.14
    unsch
    0.14
    ¦
    0.14
     lev
    0.14
    Act Density 0.029%

    No Known Activations