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

    Neuronpedia

    INDEX
    Explanations

    references to academic articles and citation formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ange
    -0.49
     naka
    -0.43
    信
    -0.42
     coni
    -0.40
    notic
    -0.39
    StrictEqual
    -0.39
    anges
    -0.39
     ivelany
    -0.38
    isRequired
    -0.38
    genous
    -0.37
    POSITIVE LOGITS
    
    0.86
    III
    0.84
     III
    0.84
     XXX
    0.84
     XL
    0.82
     VIII
    0.81
    VIII
    0.79
     XII
    0.79
    VII
    0.77
    XXX
    0.77
    Act Density 0.523%

    No Known Activations