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

    Neuronpedia

    INDEX
    Explanations

    phrases related to permissions or authorizations

    oai_token-act-pair · gpt-3.5-turbo

    negations or phrases indicating the absence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nonetheless
    -0.72
    iership
    -0.68
    elli
    -0.61
    knit
    -0.61
    wart
    -0.60
    minster
    -0.60
    grass
    -0.59
     Cathy
    -0.58
     nevertheless
    -0.58
    mill
    -0.58
    POSITIVE LOGITS
    vel
    0.94
     longer
    0.94
    ct
    0.90
    ise
    0.86
    zzle
    0.86
    except
    0.83
     matter
    0.83
    otrop
    0.81
    xious
    0.81
    vae
    0.79
    Act Density 0.054%

    No Known Activations