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

    Neuronpedia

    INDEX
    Explanations

    phrases related to registration or creating an account

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "register" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Galile
    -0.78
    ilitarian
    -0.73
    wich
    -0.72
    Ľ
    -0.69
    pei
    -0.69
    Īè
    -0.66
    ļé
    -0.65
    lihood
    -0.65
    jay
    -0.64
    »Ĵ
    -0.64
    POSITIVE LOGITS
    ifications
    0.86
    ifying
    0.84
    register
    0.76
    essions
    0.76
    uning
    0.75
    ifiers
    0.74
    ifiable
    0.73
    emark
    0.73
    isms
    0.71
    ession
    0.70
    Act Density 0.009%

    No Known Activations