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

    Neuronpedia

    INDEX
    Explanations

    instances where an action is being left to someone else or a group of people

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to leaving something or someone behind

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.69
    ML
    -0.69
     Annotations
    -0.66
    mx
    -0.64
    quickShipAvailable
    -0.64
    catentry
    -0.63
     ACPI
    -0.62
     Admission
    -0.59
    acca
    -0.59
     Highest
    -0.59
    POSITIVE LOGITS
     untouched
    0.88
     undone
    0.84
     unanswered
    0.83
     voic
    0.80
     unprotected
    0.77
     intact
    0.75
     regrets
    0.68
     ashes
    0.68
     unsatisf
    0.67
     footprints
    0.66
    Act Density 0.133%

    No Known Activations