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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and expressions of possibility or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inka
    -0.17
    ighton
    -0.16
    steller
    -0.15
    CSI
    -0.14
    IGH
    -0.14
    UBE
    -0.14
    phants
    -0.14
    asar
    -0.14
    ovi
    -0.14
    ÄĽr
    -0.14
    POSITIVE LOGITS
    led
    0.16
    acen
    0.15
    ÑĮе
    0.14
    onus
    0.14
    BarButton
    0.14
    bo
    0.14
    vable
    0.14
    .lambda
    0.13
    750
    0.13
     =============================================================================↵
    0.13
    Act Density 0.252%

    No Known Activations