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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating the potential usage or application of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the utilization of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesty
    -0.67
     Tale
    -0.66
     Hai
    -0.65
    gdala
    -0.62
     Rid
    -0.60
     Ariel
    -0.60
     passage
    -0.59
    mare
    -0.58
     Bam
    -0.58
    bitious
    -0.57
    POSITIVE LOGITS
     sparing
    1.04
    fully
    0.85
     interchange
    0.78
     extensively
    0.76
     exclusively
    0.75
    nesday
    0.74
    ences
    0.73
    pez
    0.68
    itars
    0.67
    heny
    0.67
    Act Density 0.046%

    No Known Activations