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

    Neuronpedia

    INDEX
    Explanations

    calls to action for subscribing to newsletters

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to signing up for newsletters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anus
    -0.68
     Brist
    -0.60
    nil
    -0.56
     smoot
    -0.56
     ILCS
    -0.55
    gypt
    -0.55
    amily
    -0.55
    otrop
    -0.54
    ãĥīãĥ©ãĤ´ãĥ³
    -0.54
    olt
    -0.53
    POSITIVE LOGITS
    ificantly
    1.16
    atories
    1.05
    ific
    0.98
    atures
    0.95
     Sign
    0.89
    ging
    0.88
    atory
    0.87
    ificant
    0.87
    Sign
    0.84
    sign
    0.77
    Act Density 0.017%

    No Known Activations