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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating logical negation or conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     so
    -0.76
     of
    -0.68
     
    -0.67
     de
    -0.67
    [toxicity=0]
    -0.66
    </em>
    -0.65
     a
    -0.64
    ↵
    -0.62
    -
    -0.60
    ,
    -0.60
    POSITIVE LOGITS
     (!
    1.36
    verwijspagina
    1.26
    (!
    1.15
    (!__
    1.13
     للمعارف
    1.11
     pleaſure
    1.05
     HasFactory
    1.04
     autorytatywna
    1.04
     nahilalakip
    1.04
     moustache
    1.01
    Act Density 0.018%

    No Known Activations