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

    Neuronpedia

    INDEX
    Explanations

    emotional reactions and personal reflections in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elli
    -0.17
     bew
    -0.15
    uber
    -0.15
    ython
    -0.15
    429
    -0.15
    è¿
    -0.15
    yped
    -0.14
    charm
    -0.14
    uted
    -0.14
    ifest
    -0.14
    POSITIVE LOGITS
     goose
    0.27
     sh
    0.27
     hairs
    0.24
     bile
    0.20
     pause
    0.20
     hack
    0.19
     uneasy
    0.18
     chill
    0.18
     gas
    0.18
     involuntary
    0.18
    Act Density 0.163%

    No Known Activations