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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "smile" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amarin
    -0.19
    emer
    -0.17
    erras
    -0.15
    اÙĨات
    -0.15
    orsch
    -0.15
    .yy
    -0.14
    anager
    -0.14
    doll
    -0.14
    agonal
    -0.14
    ibration
    -0.14
    POSITIVE LOGITS
     sm
    0.27
     Sm
    0.27
    aller
    0.24
    (sm
    0.22
    /sm
    0.21
    .SM
    0.20
    .sm
    0.19
    .Sm
    0.19
    ITH
    0.19
     smo
    0.19
    Act Density 0.016%

    No Known Activations