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

    Neuronpedia

    INDEX
    Explanations

    references to numerical data and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inden
    -0.16
    }elseif
    -0.15
    dlg
    -0.14
    berger
    -0.14
    stile
    -0.14
    jÄħ
    -0.14
    atrix
    -0.14
    lectic
    -0.13
    kick
    -0.13
    pare
    -0.13
    POSITIVE LOGITS
    vern
    0.14
    egra
    0.14
    estatus
    0.14
    ustum
    0.13
     allen
    0.13
    apper
    0.13
    etrics
    0.13
    earch
    0.13
     Hoch
    0.13
    adro
    0.13
    Act Density 0.243%

    No Known Activations