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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the potential for benefit or improvement

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating benefit or advantage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     proble
    -0.87
    mouth
    -0.77
    soDeliveryDate
    -0.74
    aleigh
    -0.74
    atum
    -0.73
    cal
    -0.72
    spawn
    -0.72
    arc
    -0.72
    oir
    -0.72
    apo
    -0.71
    POSITIVE LOGITS
     afar
    0.98
     royalties
    0.68
     hearing
    0.68
     scratch
    0.66
     mastering
    0.65
     Dominion
    0.64
     owning
    0.63
     Shutterstock
    0.62
     Unreal
    0.62
     this
    0.62
    Act Density 0.041%

    No Known Activations