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

    Neuronpedia

    INDEX
    Explanations

    instances of representation of data structures or memory allocation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     itſelf
    -0.92
    〢
    -0.88
     ſeveral
    -0.81
     themſelves
    -0.81
     الحره
    -0.78
     himſelf
    -0.77
    ſelf
    -0.76
    featureID
    -0.76
     Jefus
    -0.75
     Theſe
    -0.73
    POSITIVE LOGITS
     pro
    0.48
    kington
    0.47
    e
    0.47
     subtilis
    0.46
     //
    0.46
    GEBURTSDATUM
    0.46
    AnchorTagHelper
    0.46
    дми
    0.46
     beginnetje
    0.45
    E
    0.44
    Act Density 0.003%

    No Known Activations