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

    Neuronpedia

    INDEX
    Explanations

    words or phrases related to labeling, classification, or organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gre
    -0.15
     Powell
    -0.14
     or
    -0.14
    erea
    -0.14
    gre
    -0.14
     examples
    -0.14
     rub
    -0.14
    ritic
    -0.14
     Te
    -0.13
    raft
    -0.13
    POSITIVE LOGITS
    νηÏĤ
    0.18
    uky
    0.16
    othy
    0.15
    .communication
    0.14
    ÙĤÙĬ
    0.14
    _managed
    0.14
    OKEN
    0.14
    .builders
    0.14
    leta
    0.14
    :animated
    0.14
    Act Density 0.004%

    No Known Activations