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

    Neuronpedia

    INDEX
    Explanations

    definitions and declarations of classes, particularly those related to a specific animal hierarchy

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    revert
    -0.40
    .*")]
    -0.38
    OGND
    -0.38
     decep
    -0.37
    hi
    -0.37
     incur
    -0.37
    itsa
    -0.37
    otesi
    -0.36
    Proceso
    -0.36
    CSRF
    -0.36
    POSITIVE LOGITS
    IntoConstraints
    1.02
     enfans
    0.79
    enterOuterAlt
    0.76
    Personendaten
    0.73
    LayoutPanel
    0.72
     digitais
    0.71
     الرياضيه
    0.71
     parlant
    0.70
     traditionnels
    0.70
     préf
    0.70
    Act Density 0.103%

    No Known Activations