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

    Neuronpedia

    INDEX
    Explanations

    the phrase "in all"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "in all" followed by varying contexts or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fenrir
    -0.71
    lash
    -0.69
     Cumm
    -0.66
     Tale
    -0.64
    rouse
    -0.62
    yip
    -0.60
    potion
    -0.60
     Rouge
    -0.59
    atile
    -0.58
     Maiden
    -0.58
    POSITIVE LOGITS
     likelihood
    0.98
    ocating
    0.96
    usion
    0.94
    ogene
    0.94
     seriousness
    0.94
     respects
    0.92
     honesty
    0.89
     sorts
    0.87
     kinds
    0.86
    igator
    0.83
    Act Density 0.040%

    No Known Activations