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

    Neuronpedia

    INDEX
    Explanations

    instances where signing up for something is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sign" and variations of it related to agreements or registrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.83
    IRO
    -0.69
    »Ĵ
    -0.67
    âĨij
    -0.63
     Remastered
    -0.63
    =~=~
    -0.62
     Islands
    -0.61
     Layer
    -0.60
    BILITIES
    -0.59
    amily
    -0.58
    POSITIVE LOGITS
    atories
    1.26
    atory
    0.98
    ificantly
    0.95
    posted
    0.92
    posts
    0.90
    */(
    0.85
    post
    0.83
    ificant
    0.82
    alled
    0.82
    iff
    0.82
    Act Density 0.028%

    No Known Activations