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

    Neuronpedia

    INDEX
    Explanations

    words related to laws and legislation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter "t"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     destro
    -0.73
    éĹĺ
    -0.73
    Ø©
    -0.68
    姫
    -0.66
     condem
    -0.65
    Downloadha
    -0.64
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.64
     Accountability
    -0.64
    ãĤŃ
    -0.63
     è£ıè
    -0.63
    POSITIVE LOGITS
    ributes
    1.24
    umbling
    1.24
    ipper
    1.23
    agged
    1.21
    umbled
    1.18
    agging
    1.17
    ourn
    1.16
    ucked
    1.16
    ester
    1.15
    rolled
    1.13
    Act Density 0.019%

    No Known Activations