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

    Neuronpedia

    INDEX
    Explanations

    references to emotional or psychological states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ActionCreators
    -0.17
    .scalablytyped
    -0.15
    loat
    -0.14
    edx
    -0.14
    ereotype
    -0.14
    antz
    -0.14
    utsch
    -0.13
     scaleY
    -0.13
    essler
    -0.13
    ieten
    -0.13
    POSITIVE LOGITS
     hadn
    0.18
    RICT
    0.15
     habÃŃa
    0.15
    268
    0.14
    ris
    0.14
    Hdr
    0.13
    esen
    0.13
    -Sah
    0.13
    jos
    0.13
    -B
    0.13
    Act Density 0.678%

    No Known Activations