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

    Neuronpedia

    INDEX
    Explanations

    words related to stamps or stamping

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    izons
    -0.89
    SOURCE
    -0.77
    ctory
    -0.77
    cffffcc
    -0.76
     Kut
    -0.74
    Spoiler
    -0.70
    apist
    -0.69
    abama
    -0.68
    rawdownloadcloneembedreportprint
    -0.67
    scill
    -0.67
    POSITIVE LOGITS
    eding
    1.04
    itious
    0.82
     stamps
    0.79
    uation
    0.78
    uity
    0.76
     stamp
    0.76
    tale
    0.75
    arding
    0.74
     duty
    0.74
    ings
    0.74
    Act Density 0.054%

    No Known Activations