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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exceptions or contradictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مشين
    -0.59
    ymce
    -0.57
    WaitGroup
    -0.56
    enterOuterAlt
    -0.53
     autorytatywna
    -0.53
    extAlignment
    -0.52
    ngOnInit
    -0.51
    TagMode
    -0.51
    biamo
    -0.50
    CodeAttribute
    -0.50
    POSITIVE LOGITS
     Certainly
    1.05
     certainly
    0.91
    Certainly
    0.90
    certainly
    0.90
     jedenfalls
    0.88
     misschien
    0.71
     Depends
    0.71
     may
    0.71
    maybe
    0.69
     Possibly
    0.68
    Act Density 0.507%

    No Known Activations