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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "of."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    some of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NgModule
    -0.48
    warted
    -0.39
    pantalón
    -0.36
    NgModule
    -0.36
    rain
    -0.36
     betrayal
    -0.34
     abomination
    -0.34
     cowardice
    -0.34
     bırak
    -0.34
    heritance
    -0.34
    POSITIVE LOGITS
    utilisons
    0.55
    帖最后由
    0.52
    Aiheesta
    0.49
    fjspx
    0.49
     الاطلاع
    0.49
    참고
    0.48
     propOrder
    0.48
     '\\;'
    0.48
    __*/
    0.48
     lenker
    0.47
    Act Density 0.014%

    No Known Activations