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

    Neuronpedia

    INDEX
    Explanations

    references to actions taken, particularly in terms of decision-making or production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ipc
    -0.17
     Finger
    -0.14
    cek
    -0.14
     Florence
    -0.14
    Preference
    -0.14
     koc
    -0.14
    esco
    -0.13
    CFG
    -0.13
    ulis
    -0.13
    iful
    -0.13
    POSITIVE LOGITS
    awe
    0.15
    avenport
    0.14
    lund
    0.14
    .numpy
    0.14
    bruar
    0.14
    nof
    0.14
    оÑĪ
    0.14
    lere
    0.14
    anst
    0.13
    hold
    0.13
    Act Density 0.050%

    No Known Activations