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

    Neuronpedia

    INDEX
    Explanations

    words related to completion or fulfillment

    oai_token-act-pair · gpt-3.5-turbo

    the verb "are" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Iv
    -0.68
     dotted
    -0.63
     levels
    -0.63
     chalk
    -0.60
     Skies
    -0.57
     Ivy
    -0.57
     anywhere
    -0.57
     faces
    -0.56
     hinges
    -0.56
     Azerbai
    -0.56
    POSITIVE LOGITS
    re
    3.93
    reb
    2.12
    res
    2.11
    RE
    1.84
    rely
    1.78
    rea
    1.73
    rer
    1.65
    ret
    1.59
    ré
    1.58
    rep
    1.57
    Act Density 0.069%

    No Known Activations