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

    Neuronpedia

    INDEX
    Explanations

    instructions or requests related to interactions with users, potentially in online or written communication

    oai_token-act-pair · gpt-3.5-turbo

    references to instructions for submitting information or comments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¥µ
    -0.77
    humans
    -0.69
    fights
    -0.68
    asers
    -0.67
    react
    -0.64
    nery
    -0.62
    generation
    -0.62
     temples
    -0.61
    brids
    -0.61
    ynthesis
    -0.60
    POSITIVE LOGITS
     {*
    1.02
     initials
    0.96
     URI
    0.94
     formatted
    0.94
     URL
    0.93
     Authorization
    0.89
     clipboard
    0.89
     sender
    0.85
     captcha
    0.85
     username
    0.84
    Act Density 0.382%

    No Known Activations