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

    Neuronpedia

    INDEX
    Explanations

    statements where someone expresses their opinion on a particular topic or situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "weigh" or variations of it, particularly in the context of making decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MAL
    -0.68
    =]
    -0.68
    CVE
    -0.65
    CLASSIFIED
    -0.63
    HAEL
    -0.62
    LES
    -0.61
    BIL
    -0.60
    DEN
    -0.59
    lar
    -0.57
    STER
    -0.57
    POSITIVE LOGITS
     unison
    0.94
    clusions
    0.93
    ordinate
    0.91
     front
    0.87
    between
    0.86
    strument
    0.86
     favour
    0.85
    animate
    0.81
    wards
    0.80
    vert
    0.79
    Act Density 0.098%

    No Known Activations