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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases related to company obligations and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _sensitive
    -0.16
     Inn
    -0.15
    lama
    -0.15
    425
    -0.15
    irl
    -0.14
     Kenn
    -0.14
    ommen
    -0.14
    ackbar
    -0.14
     Morrison
    -0.14
    hend
    -0.14
    POSITIVE LOGITS
    raya
    0.18
    andon
    0.16
    eteria
    0.15
    fluid
    0.15
     fold
    0.14
    era
    0.14
    atab
    0.14
    ope
    0.13
     pod
    0.13
    vt
    0.13
    Act Density 0.000%

    No Known Activations