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

    Neuronpedia

    INDEX
    Explanations

    phrases that address the reader directly, emphasizing engagement and actions they can take

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anel
    -0.17
    ιÏĥÏĦο
    -0.17
    ÏĦÎŃ
    -0.16
    okud
    -0.15
    linkplain
    -0.15
     LinearGradient
    -0.14
     cigaret
    -0.14
    ãĥįãĥ«
    -0.14
    rais
    -0.14
    ughs
    -0.14
    POSITIVE LOGITS
    705
    0.18
    0.17
     pont
    0.16
     ben
    0.16
    ulla
    0.16
    _defs
    0.16
    'll
    0.16
     can
    0.16
     route
    0.16
    708
    0.15
    Act Density 0.064%

    No Known Activations