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

    Neuronpedia

    INDEX
    Explanations

    expressions of happiness or positivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    downloads
    -0.08
     McCabe
    -0.08
    stroy
    -0.08
    ieg
    -0.07
    λÏį
    -0.07
    ÅĻik
    -0.07
    ermo
    -0.07
    ional
    -0.07
    //{{
    -0.07
    916
    -0.07
    POSITIVE LOGITS
    -faced
    0.08
     faces
    0.07
     wide
    0.07
    -face
    0.07
     faced
    0.07
     ear
    0.07
     smile
    0.07
    ys
    0.07
     facial
    0.06
     radi
    0.06
    Act Density 0.009%

    No Known Activations