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

    Neuronpedia

    INDEX
    Explanations

    phrases related to licenses or permits

    oai_token-act-pair · gpt-3.5-turbo

    references to legal or illegal actions and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ¥µ
    -0.60
    uitive
    -0.59
    surprisingly
    -0.58
    Quant
    -0.55
    actic
    -0.54
    atform
    -0.53
    uably
    -0.53
    Requires
    -0.52
    UGC
    -0.52
    requires
    -0.52
    POSITIVE LOGITS
    )."
    1.12
    .'"
    1.05
     ..."
    1.01
    ?'"
    0.99
     âĢ¦"
    0.98
    !'"
    0.94
    '."
    0.91
    ,'"
    0.89
    ?"
    0.87
    .")
    0.85
    Act Density 1.137%

    No Known Activations