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

    Neuronpedia

    INDEX
    Explanations

    phrases or quotations that express dialogue or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avra
    -0.18
    klad
    -0.15
    idla
    -0.15
    hoe
    -0.15
    bare
    -0.14
    اعÙĬ
    -0.14
    лий
    -0.14
    Spy
    -0.14
    usted
    -0.14
    adlo
    -0.14
    POSITIVE LOGITS
    imenti
    0.15
    ame
    0.15
     according
    0.15
     says
    0.15
    .catch
    0.15
     catch
    0.15
     said
    0.14
    lied
    0.14
     ste
    0.14
    859
    0.14
    Act Density 0.091%

    No Known Activations