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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be" and its variations, indicating states of being and existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awe
    -0.16
     whipped
    -0.15
     Hoy
    -0.15
    /setup
    -0.15
    oka
    -0.15
    iene
    -0.15
     masturb
    -0.15
     chopping
    -0.14
     lur
    -0.14
     harass
    -0.14
    POSITIVE LOGITS
     doing
    0.29
     making
    0.28
     taking
    0.23
     trying
    0.21
     giving
    0.20
     going
    0.20
     working
    0.19
     putting
    0.19
     able
    0.19
     using
    0.19
    Act Density 0.479%

    No Known Activations