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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating doubt or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oul
    -0.12
    ifik
    -0.12
    ordion
    -0.12
    plode
    -0.11
    abee
    -0.11
    irit
    -0.11
    alach
    -0.11
    ripper
    -0.11
    gue
    -0.11
    zos
    -0.11
    POSITIVE LOGITS
    -Ta
    0.12
    xious
    0.12
    OWN
    0.12
    .Async
    0.12
     seller
    0.11
    ëĶĶìĭľ
    0.11
    격
    0.11
     venda
    0.11
    jedn
    0.11
    _WM
    0.11
    Act Density 0.066%

    No Known Activations