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

    Neuronpedia

    INDEX
    Explanations

    email newsletter sign-up prompts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Sign" related to signing up for newsletters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    »Ĵ
    -0.82
    ãĥīãĥ©ãĤ´ãĥ³
    -0.76
    ooked
    -0.76
     nerv
    -0.75
    ĸļ
    -0.70
    @#&
    -0.69
    amily
    -0.68
    ETHOD
    -0.68
    olt
    -0.66
    ISION
    -0.65
    POSITIVE LOGITS
    atories
    1.21
     Sign
    1.21
    ificantly
    1.16
    ific
    1.12
    Sign
    1.12
    atures
    1.04
    sign
    0.98
    atory
    0.96
    ging
    0.93
    zai
    0.91
    Act Density 0.012%

    No Known Activations