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

    Neuronpedia

    INDEX
    Explanations

    instances of last-minute decisions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odos
    -0.17
    isman
    -0.16
    541
    -0.14
    leton
    -0.14
    _LP
    -0.14
     sooner
    -0.14
    fer
    -0.13
     Pixels
    -0.13
    _Port
    -0.13
    ISMATCH
    -0.13
    POSITIVE LOGITS
     ele
    0.43
     last
    0.34
     late
    0.32
    ele
    0.30
     Ele
    0.29
     at
    0.29
    -last
    0.28
     última
    0.27
    .last
    0.26
     dernière
    0.26
    Act Density 0.062%

    No Known Activations