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

    Neuronpedia

    INDEX
    Explanations

    verbs related to solidifying or finalizing something

    oai_token-act-pair · gpt-3.5-turbo

    words related to processes of confirmation or completion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mehran
    -0.65
    mong
    -0.64
     cents
    -0.63
     Loft
    -0.62
     mouths
    -0.60
     Mace
    -0.60
     brow
    -0.60
    bill
    -0.59
     ILCS
    -0.58
     Mistress
    -0.58
    POSITIVE LOGITS
    Completed
    0.77
    irmation
    0.77
    uctor
    0.73
    atively
    0.73
     fulfillment
    0.73
    rity
    0.72
    ATIONS
    0.71
    foundation
    0.69
    uberty
    0.67
     acceptance
    0.67
    Act Density 0.119%

    No Known Activations