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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating obligation or assertion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =Value
    -0.15
    pollo
    -0.15
    ãĥĥãĥĪ
    -0.14
    isclosed
    -0.14
    quisition
    -0.14
    igg
    -0.14
    usk
    -0.14
    799
    -0.13
    ucket
    -0.13
    nier
    -0.13
    POSITIVE LOGITS
     incumbent
    0.25
     vit
    0.23
     past
    0.20
     urgent
    0.20
     vital
    0.19
    urgent
    0.19
     critically
    0.18
     Past
    0.18
     essential
    0.18
     critical
    0.17
    Act Density 0.133%

    No Known Activations