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

    Neuronpedia

    INDEX
    Explanations

    specific programming or API-related terminology, particularly related to resource management

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Carver
    -0.53
    <u>
    -0.51
     har
    -0.51
    </b>
    -0.48
    queryInterface
    -0.47
     run
    -0.45
    <i>
    -0.43
     ran
    -0.42
    í
    -0.42
    <b>
    -0.41
    POSITIVE LOGITS
     الحره
    0.81
    UnsafeEnabled
    0.81
     Theſe
    0.78
     Houſe
    0.76
     autorytatywna
    0.75
    Chham
    0.74
     myſelf
    0.73
    toThrow
    0.73
     Beſ
    0.73
     Reſ
    0.73
    Act Density 0.032%

    No Known Activations