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

    Neuronpedia

    INDEX
    Explanations

    mentions of legislative or governmental actions and procedures

    oai_token-act-pair · gpt-3.5-turbo

    the frequent use of the word "the" in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     whilst
    -0.74
     besides
    -0.73
    !!!!
    -0.71
    !!!
    -0.71
    \'
    -0.69
    =""
    -0.68
    adoes
    -0.66
    ibl
    -0.66
    Layer
    -0.65
    lime
    -0.65
    POSITIVE LOGITS
     latter
    1.17
     nation
    1.13
     country
    1.12
     latest
    1.11
     Kremlin
    1.06
     same
    1.05
     president
    1.02
    ocratic
    1.01
     United
    0.98
    resa
    0.95
    Act Density 1.315%

    No Known Activations