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

    Neuronpedia

    INDEX
    Explanations

    mentions of laboratory-related terms and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eous
    -0.19
    orque
    -0.18
    esses
    -0.17
    ambda
    -0.16
    atego
    -0.15
    گاÙĨ
    -0.15
    ibar
    -0.14
    quam
    -0.14
    abella
    -0.14
    gard
    -0.14
    POSITIVE LOGITS
    elling
    0.30
    /lab
    0.26
    rador
    0.26
    bers
    0.22
    atory
    0.20
    rary
    0.18
    VIEW
    0.18
    室
    0.18
    coat
    0.18
     lab
    0.17
    Act Density 0.015%

    No Known Activations