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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparisons or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ACHI
    -0.16
    ande
    -0.15
     Alic
    -0.15
    onder
    -0.15
    OP
    -0.15
    achi
    -0.14
    unga
    -0.14
     Altern
    -0.14
    Ĥæķ°
    -0.14
    ertools
    -0.14
    POSITIVE LOGITS
    MPI
    0.17
    ahat
    0.15
    ulg
    0.15
    etat
    0.15
    765
    0.14
    رÙģتÙĩ
    0.14
    ram
    0.14
    Tpl
    0.13
    .dtp
    0.13
    _malloc
    0.13
    Act Density 0.146%

    No Known Activations