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

    Neuronpedia

    INDEX
    Explanations

    statements of existence or non-existence along with related verbs like "is" and "are"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.99
     Administrativna
    -0.90
    ^(@)
    -0.88
     Jefus
    -0.80
     للمعارف
    -0.79
     $_"
    -0.79
     Houſe
    -0.78
    ReusableCell
    -0.75
     NDEBUG
    -0.75
    cuerdo
    -0.74
    POSITIVE LOGITS
    InjectAttribute
    0.72
    <eos>
    0.67
    ↵↵
    0.67
    .
    0.46
    })$.
    0.46
    ]),
    0.44
    努
    0.43
    ↵↵↵↵↵↵↵↵↵
    0.43
    ↵↵↵↵↵↵↵
    0.43
     This
    0.43
    Act Density 0.467%

    No Known Activations