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

    Neuronpedia

    INDEX
    Explanations

    references to signing up for newsletters or services

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "signing" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.80
    agy
    -0.79
     Islands
    -0.74
     ILCS
    -0.71
    irth
    -0.68
    ooked
    -0.68
    ¬¼
    -0.66
    Pg
    -0.65
     Surviv
    -0.64
    »Ĵ
    -0.63
    POSITIVE LOGITS
    */(
    1.02
    atories
    0.96
    atory
    0.91
    ific
    0.81
    ifying
    0.79
    chant
    0.78
    uary
    0.76
    ifiers
    0.75
    eering
    0.75
    ificantly
    0.75
    Act Density 0.023%

    No Known Activations