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

    Neuronpedia

    INDEX
    Explanations

    phrases related to stating or emphasizing facts or claims

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "substantiate" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Doodle
    -0.80
    giving
    -0.76
     marrow
    -0.74
    bench
    -0.73
    fork
    -0.72
    Pear
    -0.72
    jack
    -0.72
    FAULT
    -0.70
    keeper
    -0.68
    lder
    -0.67
    POSITIVE LOGITS
    iated
    1.32
    ially
    1.18
    iate
    1.13
    iating
    1.07
    iation
    1.03
    imated
    1.01
    iates
    0.98
    opoulos
    0.98
    rons
    0.94
    etrical
    0.92
    Act Density 0.021%

    No Known Activations