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

    Neuronpedia

    INDEX
    Explanations

    expressions of positive sentiment and emotional connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usch
    -0.15
    Ã
    -0.14
    째
    -0.14
     हत
    -0.14
    estate
    -0.13
    ishly
    -0.13
    izik
    -0.13
    RID
    -0.13
    ield
    -0.13
    ely
    -0.13
    POSITIVE LOGITS
    uki
    0.16
     Elem
    0.16
    705
    0.15
     Pik
    0.14
    ког
    0.14
    dash
    0.14
    raquo
    0.14
    632
    0.14
     Dank
    0.13
    779
    0.13
    Act Density 0.352%

    No Known Activations