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

    Neuronpedia

    INDEX
    Explanations

    words related to technology features and functionalities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    hu
    -0.71
    ptives
    -0.68
    culosis
    -0.67
    anium
    -0.62
    auri
    -0.60
    minent
    -0.60
    itiz
    -0.59
    obyl
    -0.58
    resents
    -0.58
     frames
    -0.57
    POSITIVE LOGITS
    .,
    0.69
    !:
    0.67
     elusive
    0.61
    .:
    0.61
    !,
    0.60
     Rasm
    0.60
    ,,
    0.59
     forgive
    0.59
    .
    0.59
    .-
    0.59
    Act Density 0.114%

    No Known Activations