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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating agreement or alignment with a particular choice or opinion

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate associations and relationships involving the words "by" and "with."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aeus
    -0.73
    Applic
    -0.72
    Bay
    -0.71
    Ire
    -0.71
    COL
    -0.69
    Letter
    -0.68
    Cook
    -0.67
    Benef
    -0.66
    UCT
    -0.66
    -+-+
    -0.65
    POSITIVE LOGITS
     unnoticed
    0.85
     undet
    0.78
     stairs
    0.75
    eper
    0.67
    ramid
    0.65
    erk
    0.64
     shopping
    0.63
    onz
    0.62
    vt
    0.62
    annis
    0.62
    Act Density 0.067%

    No Known Activations