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

    Neuronpedia

    INDEX
    Explanations

    phrases related to signing up for services, memberships, or subscriptions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to signing up for services or subscriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omal
    -0.74
    cock
    -0.65
    ument
    -0.63
    ĸļ
    -0.62
    wich
    -0.61
    put
    -0.60
    kel
    -0.56
    slice
    -0.56
     Mecca
    -0.56
    phy
    -0.55
    POSITIVE LOGITS
    lish
    0.73
     for
    0.71
    à¼
    0.67
    acts
    0.65
    osponsors
    0.63
    leased
    0.63
    ername
    0.63
    */(
    0.62
    river
    0.61
    usercontent
    0.61
    Act Density 0.040%

    No Known Activations