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

    Neuronpedia

    INDEX
    Explanations

    references to significant achievements or milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fascinated
    -0.16
     fasc
    -0.16
    indow
    -0.16
     provoc
    -0.15
    enson
    -0.15
     Impress
    -0.15
    uÄį
    -0.14
    ÑĢок
    -0.14
     mourn
    -0.14
    idi
    -0.14
    POSITIVE LOGITS
     accomplishment
    0.24
     surreal
    0.24
     pinch
    0.23
     Validation
    0.23
     emotional
    0.23
     validation
    0.23
     emotions
    0.23
    Validation
    0.20
     achievement
    0.20
     vind
    0.20
    Act Density 0.198%

    No Known Activations