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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal sentiments and emotional states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abad
    -0.22
    Dll
    -0.18
     Cly
    -0.16
    ToBounds
    -0.16
    DIV
    -0.16
    bÃŃr
    -0.15
    ipa
    -0.14
    emode
    -0.14
    uede
    -0.14
    anela
    -0.14
    POSITIVE LOGITS
     committed
    0.30
    committed
    0.23
     commit
    0.22
     cogn
    0.22
     COMMIT
    0.21
     commitment
    0.21
     grat
    0.20
     Commit
    0.20
     grav
    0.19
     confident
    0.19
    Act Density 0.089%

    No Known Activations