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

    Neuronpedia

    INDEX
    Explanations

    names and specific terms related to "Abandon"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     multiplier
    -0.74
     Mosque
    -0.69
     Zh
    -0.65
     Throne
    -0.61
     Witnesses
    -0.61
     punch
    -0.60
     feast
    -0.60
     detectives
    -0.59
     sched
    -0.59
     Number
    -0.59
    POSITIVE LOGITS
    andon
    4.74
    kees
    1.09
    amar
    1.01
    duct
    0.99
    raham
    0.98
    agra
    0.97
    lear
    0.94
    anyon
    0.92
    cair
    0.92
    roud
    0.90
    Act Density 0.024%

    No Known Activations