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

    Neuronpedia

    INDEX
    Explanations

    words that convey intensity or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Patch
    -0.17
    aille
    -0.16
    Patch
    -0.16
     patches
    -0.15
    patches
    -0.15
    _patch
    -0.15
    strup
    -0.15
     Pitch
    -0.14
     patch
    -0.14
    AILABLE
    -0.14
    POSITIVE LOGITS
    akan
    0.17
    apos
    0.17
     prom
    0.16
    Ľå»º
    0.15
    ene
    0.14
     åIJ
    0.14
    redit
    0.14
    old
    0.14
    ane
    0.14
     old
    0.14
    Act Density 0.003%

    No Known Activations