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

    Neuronpedia

    INDEX
    Explanations

    instances of event cancellations and related details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ild
    -0.15
     reint
    -0.15
    osaur
    -0.14
     reconc
    -0.14
    ÃŃst
    -0.14
    MLS
    -0.14
    ove
    -0.14
    맹
    -0.14
    еви
    -0.14
    uptools
    -0.13
    POSITIVE LOGITS
     cancel
    0.67
     cancellation
    0.62
     Cancel
    0.62
     cancell
    0.61
     canc
    0.57
    Cancel
    0.56
    -cancel
    0.56
    .cancel
    0.56
    cancel
    0.56
     cancelled
    0.55
    Act Density 0.040%

    No Known Activations