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

    Neuronpedia

    INDEX
    Explanations

    references to organizational structures and authority figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alam
    -0.17
    ORMAT
    -0.16
    ptune
    -0.15
    adera
    -0.15
    importe
    -0.15
    imentos
    -0.15
    enties
    -0.14
    Zoom
    -0.14
    coni
    -0.14
    avia
    -0.14
    POSITIVE LOGITS
     Charm
    0.19
    odynam
    0.18
    ève
    0.17
    ê
    0.15
    aby
    0.15
    yk
    0.15
    æķĪ
    0.14
    fast
    0.14
    ree
    0.14
    gang
    0.14
    Act Density 0.043%

    No Known Activations