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

    Neuronpedia

    INDEX
    Explanations

    phrases related to signing up for newsletters or services

    oai_token-act-pair · gpt-3.5-turbo

    mentions of signing up for services or mailing lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    »Ĵ
    -0.72
     DRAG
    -0.64
     luck
    -0.62
     nerv
    -0.58
    IRO
    -0.57
     bare
    -0.56
    iron
    -0.56
     nut
    -0.56
    ught
    -0.56
     impart
    -0.56
    POSITIVE LOGITS
    ificantly
    1.70
    ificant
    1.68
    atures
    1.53
    atories
    1.41
    ature
    1.39
    ific
    1.39
    ATURES
    1.17
    posts
    1.11
    atory
    1.07
    aling
    1.07
    Act Density 0.020%

    No Known Activations