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

    Neuronpedia

    INDEX
    Explanations

    forms of deception or concealment

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    <eos>
    -0.59
    <bos>
    -0.50
     tendência
    -0.50
    Personensuche
    -0.48
     respectively
    -0.48
    ↵
    -0.47
    Derbyniad
    -0.44
     saling
    -0.43
    ↵↵
    -0.42
        
    -0.41
    POSITIVE LOGITS
    PhysRevD
    0.99
    SequentialGroup
    0.95
    tagext
    0.94
    MLLoader
    0.92
    WriteBarrier
    0.92
    StoryboardSegue
    0.82
    __':
    0.79
    fjspx
    0.77
    ništ
    0.77
     Wicidata
    0.76
    Act Density 0.076%

    No Known Activations