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

    Neuronpedia

    INDEX
    Explanations

    specific programming or mathematical syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nosaurus
    -0.61
    }';
    -0.60
    dymyr
    -0.60
    quirer
    -0.59
    [toxicity=0]
    -0.58
    fecture
    -0.55
    -
    -0.55
    orrhea
    -0.53
    AutoField
    -0.53
    quium
    -0.53
    POSITIVE LOGITS
     myſelf
    1.30
     himſelf
    1.26
     itſelf
    1.23
    ſelves
    1.15
     Anſ
    1.15
     Jefus
    1.14
     themſelves
    1.12
    ſelf
    1.12
     Conſ
    1.12
     Reſ
    1.10
    Act Density 0.930%

    No Known Activations