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

    Neuronpedia

    INDEX
    Explanations

    words related to the action of lessening or shortening something

    oai_token-act-pair · gpt-3.5-turbo

    variations of verbs that suggest reduction or decrease

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thirds
    -0.68
     guidance
    -0.64
     Crist
    -0.61
    llan
    -0.61
     semif
    -0.60
     Hulk
    -0.58
    holding
    -0.58
    puting
    -0.58
     Rica
    -0.58
     Semin
    -0.57
    POSITIVE LOGITS
    inki
    1.03
    undown
    0.97
    atche
    0.88
    ened
    0.85
    burgh
    0.83
    emies
    0.83
    chant
    0.82
    baugh
    0.82
    ococ
    0.81
    kinson
    0.77
    Act Density 0.018%

    No Known Activations