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

    Neuronpedia

    INDEX
    Explanations

    phrases related to giving up or relinquishing control

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "abandon" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sphere
    -0.68
     Wow
    -0.67
    ior
    -0.65
    pes
    -0.60
    ional
    -0.59
    Law
    -0.59
    urga
    -0.59
    ith
    -0.59
    icka
    -0.58
     representing
    -0.58
    POSITIVE LOGITS
     abandon
    3.60
     abandoning
    1.89
     abandonment
    1.80
     Abandon
    1.54
     abandoned
    1.52
     disregard
    1.46
     fors
    1.36
     discard
    1.30
     ditch
    1.18
     adopt
    1.17
    Act Density 0.012%

    No Known Activations