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

    Neuronpedia

    INDEX
    Explanations

    phrases related to caution or warning

    oai_token-act-pair · gpt-3.5-turbo

    references to authority figures or experts discussing policy or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    surprisingly
    -0.72
     Slate
    -0.60
    !:
    -0.60
     Reborn
    -0.59
     Eater
    -0.57
    ãĥį
    -0.57
     Yon
    -0.56
     Edited
    -0.56
     Edit
    -0.55
     echoed
    -0.55
    POSITIVE LOGITS
    )."
    1.49
     ..."
    1.39
    ),"
    1.33
    ',"
    1.30
    ,'"
    1.30
    )",
    1.26
     âĢ¦"
    1.25
    ."
    1.25
    .'"
    1.25
    .""
    1.23
    Act Density 2.127%

    No Known Activations