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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    specific vowel sounds in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ADRA
    -0.74
    INAL
    -0.68
    actionDate
    -0.67
     bearer
    -0.63
     shenan
    -0.62
     tremend
    -0.62
     millenn
    -0.61
    milo
    -0.61
     indo
    -0.60
    reason
    -0.60
    POSITIVE LOGITS
    velt
    0.86
    ttes
    0.86
    etus
    0.83
    phant
    0.81
     QC
    0.80
    wu
    0.79
    heid
    0.75
    yne
    0.75
    icz
    0.74
     Gardens
    0.72
    Act Density 0.352%

    No Known Activations