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

    Neuronpedia

    INDEX
    Explanations

    phrases related to providing knowledge or understanding about a particular topic

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey understanding or perception of a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     disbanded
    -0.67
    ony
    -0.64
     Balanced
    -0.63
    onies
    -0.62
     Musical
    -0.61
    annis
    -0.61
     Postal
    -0.58
    eh
    -0.58
     Grave
    -0.58
    ÄŁ
    -0.58
    POSITIVE LOGITS
     insights
    1.06
     insight
    1.06
    ibility
    0.90
     guiActiveUn
    0.88
     glean
    0.81
    ively
    0.80
    ritional
    0.78
    iasco
    0.77
    spection
    0.77
    spective
    0.76
    Act Density 0.009%

    No Known Activations