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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the generation or creation of ideas or solutions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference the action of coming up with ideas or solutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewed
    -0.68
     CLSID
    -0.66
     Austral
    -0.65
    Ore
    -0.64
    Synopsis
    -0.63
    gee
    -0.62
     Bezos
    -0.60
     Aliens
    -0.60
    =]
    -0.59
    iquid
    -0.58
    POSITIVE LOGITS
    river
    0.84
    stairs
    0.81
    stage
    0.76
    sted
    0.74
    cycles
    0.73
    rocal
    0.70
    ester
    0.66
    endra
    0.66
    rance
    0.66
    rison
    0.66
    Act Density 0.024%

    No Known Activations