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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate impactful events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eme
    -0.18
    kim
    -0.15
    paren
    -0.15
    .advance
    -0.14
    _unref
    -0.14
     æħ
    -0.14
    ãĤ
    -0.14
    ical
    -0.14
    меÑī
    -0.14
    istar
    -0.14
    POSITIVE LOGITS
     jackpot
    0.21
     harder
    0.20
     hard
    0.19
     hit
    0.17
     Hard
    0.17
     pause
    0.17
     hitting
    0.17
     stride
    0.16
     targets
    0.16
     hardest
    0.16
    Act Density 0.036%

    No Known Activations