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

    Neuronpedia

    INDEX
    Explanations

    proper names or specific entities, such as names of people or places

    oai_token-act-pair · gpt-3.5-turbo

    names and specific terms associated with locations and characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dan
    -0.72
    mits
    -0.70
    rien
    -0.70
    nan
    -0.70
    making
    -0.70
    RESULTS
    -0.70
    NOR
    -0.69
    cru
    -0.69
    Cru
    -0.69
    MIT
    -0.68
    POSITIVE LOGITS
    usk
    0.91
    wana
    0.91
    ulu
    0.90
    iple
    0.82
    zar
    0.80
    wark
    0.76
    aiman
    0.76
    elta
    0.76
    arde
    0.75
     Nadu
    0.74
    Act Density 0.008%

    No Known Activations