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

    Neuronpedia

    INDEX
    Explanations

    references to time indicators and specific locations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    –and
    -0.49
    –
    -0.45
    –↵↵
    -0.44
    .–
    -0.40
    ––
    -0.35
    âĶĢâĶĢ
    -0.31
    ————
    -0.26
    âĢIJâĢIJ
    -0.24
    )—
    -0.24
    ,—
    -0.24
    POSITIVE LOGITS
     -
    0.99
     -↵
    0.69
     -↵↵
    0.55
     -,
    0.49
     -.
    0.46
     -(
    0.43
     -*
    0.40
     -:
    0.37
     -$
    0.36
     -=
    0.33
    Act Density 0.336%

    No Known Activations