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

    Neuronpedia

    INDEX
    Explanations

    words related to newsletter subscriptions

    oai_token-act-pair · gpt-3.5-turbo

    calls to action related to signing up for newsletters or mailing lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    »Ĵ
    -0.74
    ĸļ
    -0.73
     nerv
    -0.72
    ãĥīãĥ©ãĤ´ãĥ³
    -0.70
    amily
    -0.70
    ooked
    -0.67
     Pwr
    -0.65
     ILCS
    -0.65
     Islands
    -0.63
    IRO
    -0.63
    POSITIVE LOGITS
    ificantly
    1.41
    atories
    1.38
    atures
    1.22
    ific
    1.21
    ificant
    1.16
    atory
    1.16
    ging
    1.04
    Sign
    1.04
    ifying
    1.03
     Sign
    1.01
    Act Density 0.019%

    No Known Activations