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

    Neuronpedia

    INDEX
    Explanations

    numerical information or indicators related to five and other counts associated with entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "
    -0.77
     
    -0.76
     “
    -0.76
     he
    -0.71
     as
    -0.66
     I
    -0.65
     +
    -0.64
     a
    -0.63
    }}}}
    -0.60
     ...
    -0.60
    POSITIVE LOGITS
     Cæsar
    1.13
     itſelf
    1.08
    soever
    1.06
     Shakspeare
    1.04
    withstanding
    1.04
     Monfieur
    1.02
     photolibrary
    0.96
     Majefty
    0.95
     ſhe
    0.95
     myſelf
    0.95
    Act Density 0.125%

    No Known Activations