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

    Neuronpedia

    INDEX
    Explanations

    words related to rapid movements or actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "br"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.76
     Decay
    -0.76
    ãĤ®
    -0.71
     AMERICA
    -0.70
     Contra
    -0.70
    WARE
    -0.67
    BOX
    -0.66
    IELD
    -0.66
    EVA
    -0.65
    ãĥ¼ãĥĨãĤ£
    -0.65
    POSITIVE LOGITS
    itt
    1.05
    idget
    1.01
    ighter
    0.99
    agged
    0.98
    acket
    0.96
    agg
    0.96
    ag
    0.95
    achy
    0.94
    icked
    0.93
    acing
    0.92
    Act Density 0.007%

    No Known Activations