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

    Neuronpedia

    INDEX
    Explanations

    where something originates from

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to origins or sources of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    perty
    -0.82
    seek
    -0.80
    availability
    -0.75
    ciples
    -0.72
    olson
    -0.72
    isode
    -0.71
    merce
    -0.70
    escription
    -0.69
    idav
    -0.68
    icators
    -0.67
    POSITIVE LOGITS
     afar
    1.14
     somewhere
    0.99
     scratch
    0.93
     whence
    0.89
     abroad
    0.88
     nowhere
    0.83
     anywhere
    0.79
     elsewhere
    0.78
     behind
    0.77
     thence
    0.70
    Act Density 0.078%

    No Known Activations