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

    Neuronpedia

    INDEX
    Explanations

    certain repeated symbols or characters, indicating formatting or structural elements within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CPR
    -0.15
    TRS
    -0.14
    ’S
    -0.14
    .documentation
    -0.14
     CET
    -0.14
    VR
    -0.14
     CRT
    -0.14
    LR
    -0.13
     ‘
    -0.13
    createCommand
    -0.13
    POSITIVE LOGITS
     BI
    0.39
     NI
    0.36
     SI
    0.34
     CI
    0.33
    BI
    0.31
     WI
    0.30
    SI
    0.30
    WI
    0.30
    NI
    0.29
    CI
    0.29
    Act Density 0.004%

    No Known Activations