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

    Neuronpedia

    INDEX
    Explanations

    legal terminology and citation formats

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    <eos>
    -0.42
    ...
    -0.40
     et
    -0.40
    de
    -0.38
     
    -0.38
    ↵↵
    -0.37
     A
    -0.37
     E
    -0.37
     Q
    -0.37
    con
    -0.36
    POSITIVE LOGITS
     pleaſure
    1.17
     Reſ
    1.16
    ^(@)
    1.13
     Diſ
    1.09
     itſelf
    1.09
    ſelf
    1.08
     poffe
    1.08
     Monfieur
    1.06
     Majefty
    1.05
     ſmall
    1.05
    Act Density 0.010%

    No Known Activations