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

    Neuronpedia

    INDEX
    Explanations

    instances where something is being done or happening to specific entities or objects

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating actions related to ongoing situations or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ranking
    -0.72
     trailing
    -0.71
     rating
    -0.66
     succession
    -0.65
     testament
    -0.64
     distinction
    -0.63
     hesitation
    -0.62
     knack
    -0.62
     genesis
    -0.59
     issuer
    -0.58
    POSITIVE LOGITS
    quished
    0.87
    ocene
    0.83
    igated
    0.80
    ictionary
    0.77
    uries
    0.75
    Ú
    0.74
    姫
    0.74
    otyp
    0.73
    qqa
    0.73
    leground
    0.72
    Act Density 0.107%

    No Known Activations