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

    Neuronpedia

    INDEX
    Explanations

    mentions of the number one or references to minimal quantities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.65
     juste
    -0.63
     Exactly
    -0.60
    /*
    -0.57
     pobreza
    -0.55
     doucement
    -0.54
     justa
    -0.54
    Exactly
    -0.53
    obut
    -0.53
     exactly
    -0.53
    POSITIVE LOGITS
     فريبيس
    0.74
    -------
    0.70
     noDo
    0.69
    mbggenerated
    0.61
    martre
    0.59
     ibi
    0.58
    WebVitals
    0.58
    MLLoader
    0.57
     multiple
    0.55
    ViewFeatures
    0.55
    Act Density 0.248%

    No Known Activations