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

    Neuronpedia

    INDEX
    Explanations

    phrases or instances related to signing up for different services, agreements, or subscriptions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "sign."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.83
    »Ĵ
    -0.68
    IRO
    -0.65
    âĨij
    -0.65
    ecause
    -0.65
    =~=~
    -0.63
    amily
    -0.61
    @#&
    -0.60
     nerv
    -0.59
    ORGE
    -0.58
    POSITIVE LOGITS
    atories
    1.33
    ificantly
    1.02
    atory
    1.01
    posts
    0.93
    ifying
    0.86
    posted
    0.86
    ific
    0.85
    alled
    0.84
    ificant
    0.84
    iff
    0.82
    Act Density 0.024%

    No Known Activations