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

    Neuronpedia

    INDEX
    Explanations

    references to time or specific dates

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    avorite
    -1.09
    ortium
    -1.07
    rosis
    -0.98
    ancial
    -0.96
    ourt
    -0.95
    itary
    -0.93
    alach
    -0.90
    irie
    -0.89
    inav
    -0.89
     Nig
    -0.87
    POSITIVE LOGITS
    spe
    1.00
    liest
    0.91
    frames
    0.90
    code
    0.87
     behest
    0.86
     urging
    0.84
     hierarchy
    0.84
    isch
    0.81
    à¼
    0.79
     Thiel
    0.78
    Act Density 0.656%

    No Known Activations