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

    Neuronpedia

    INDEX
    Explanations

    sentences related to discussing or reporting events or situations

    oai_token-act-pair · gpt-3.5-turbo

    statements expressing opinions or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ®
    -0.75
     guiActiveUn
    -0.71
    iru
    -0.70
     Amid
    -0.69
    îĢ
    -0.69
    ³³³³³³³³
    -0.69
     «
    -0.68
    ?,
    -0.68
    ³³³
    -0.67
    surprisingly
    -0.66
    POSITIVE LOGITS
    .'"
    0.90
    .")
    0.84
    )."
    0.80
    .""
    0.76
     everybody
    0.76
    ."
    0.73
    }"
    0.70
    '."
    0.70
    entimes
    0.68
     somebody
    0.67
    Act Density 0.905%

    No Known Activations