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

    Neuronpedia

    INDEX
    Explanations

    references to events that have been postponed or rescheduled

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alu
    -0.16
     hurry
    -0.15
     shrink
    -0.15
    tru
    -0.14
    rita
    -0.14
     species
    -0.14
    ibaba
    -0.14
    åħ¥
    -0.14
    á»ī
    -0.14
     Disk
    -0.13
    POSITIVE LOGITS
     postpone
    0.21
     postponed
    0.20
     postpon
    0.20
     cancell
    0.20
     cancellation
    0.19
     res
    0.19
     defer
    0.19
    -cancel
    0.18
     Cancel
    0.18
    Cancel
    0.17
    Act Density 0.022%

    No Known Activations