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

    Neuronpedia

    INDEX
    Explanations

    websites or online platforms

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    arians
    -0.87
    osphere
    -0.78
     Archdemon
    -0.71
     Collider
    -0.69
    ibal
    -0.69
    icity
    -0.68
    IRO
    -0.67
    iser
    -0.65
    ajor
    -0.64
    ational
    -0.64
    POSITIVE LOGITS
    coon
    0.99
    kes
    0.83
    marine
    0.78
    ping
    0.78
    faces
    0.77
    raq
    0.77
    les
    0.77
    bors
    0.76
    fing
    0.76
    pes
    0.76
    Act Density 0.034%

    No Known Activations