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

    Neuronpedia

    INDEX
    Explanations

    verbs related to looking, finding, and searching

    oai_token-act-pair · gpt-3.5-turbo

    actions related to searching, checking, or retrieving something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     penchant
    -0.65
     Created
    -0.63
     ISBN
    -0.62
     divided
    -0.61
     Subtle
    -0.61
     indic
    -0.61
    riad
    -0.60
     Saga
    -0.60
    Ability
    -0.60
     knack
    -0.58
    POSITIVE LOGITS
    achu
    0.78
    tackle
    0.77
    igate
    0.75
    mage
    0.74
    orate
    0.73
    BIL
    0.73
     mosqu
    0.72
    ettle
    0.70
    lead
    0.70
    oti
    0.70
    Act Density 0.286%

    No Known Activations