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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting symbols that may indicate transitions or emphasis in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _C
    -0.18
    B
    -0.18
    _S
    -0.18
    C
    -0.18
    G
    -0.18
    M
    -0.18
    N
    -0.18
    F
    -0.18
    P
    -0.18
    _P
    -0.17
    POSITIVE LOGITS
    Advertisements
    0.25
     “
    0.22
    Enlarge
    0.21
    Narrated
    0.21
     If
    0.21
     Read
    0.21
     This
    0.20
     It
    0.20
     In
    0.19
    Submitting
    0.19
    Act Density 1.577%

    No Known Activations