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

    Neuronpedia

    INDEX
    Explanations

    words related to specific products or brands

    oai_token-act-pair · gpt-3.5-turbo

    references to specific products or brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensical
    -0.75
    ASED
    -0.74
     ACTIONS
    -0.71
     citiz
    -0.67
    åº
    -0.67
    zona
    -0.66
    ãĥīãĥ©
    -0.64
    orney
    -0.62
    tenance
    -0.62
    Lago
    -0.61
    POSITIVE LOGITS
    espie
    0.75
    atra
    0.66
     Sne
    0.65
     Sheen
    0.64
    ittens
    0.62
     Furious
    0.61
     creeps
    0.61
    terness
    0.60
    indal
    0.60
     filament
    0.59
    Act Density 0.892%

    No Known Activations