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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific dates along with related actions or events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of violence or threats associated with specific events or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .''
    -0.72
    ''.
    -0.64
    .�
    -0.63
    .""
    -0.62
    ."[
    -0.62
    ]."
    -0.59
    .","
    -0.58
    ".[
    -0.58
    .''.
    -0.57
    âĢij
    -0.56
    POSITIVE LOGITS
    lez
    0.54
     Canaver
    0.51
     Blizz
    0.50
     Femin
    0.50
     Patreon
    0.48
     Dunham
    0.48
     adorable
    0.48
     Blizzard
    0.48
     Zoro
    0.47
    Pokemon
    0.47
    Act Density 3.290%

    No Known Activations