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

    Neuronpedia

    INDEX
    Explanations

    words or phrases indicating examples or instances of a concept

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'e' in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lifes
    -0.59
     Shot
    -0.58
     shroud
    -0.57
     poppy
    -0.56
    roller
    -0.55
     Bullet
    -0.55
     Shroud
    -0.54
     unpre
    -0.53
     fet
    -0.53
     Conversation
    -0.53
    POSITIVE LOGITS
    pecially
    0.95
    -)
    0.85
    %),
    0.84
    umably
    0.83
    viously
    0.82
    ardless
    0.78
    esides
    0.78
    )
    0.78
    terday
    0.78
    lihood
    0.77
    Act Density 0.072%

    No Known Activations