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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    the presence of blank or empty sections in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zona
    -0.74
     Strip
    -0.71
     DPR
    -0.66
    ĵĺ
    -0.66
     bottleneck
    -0.65
     totality
    -0.64
     compromising
    -0.63
     Cerberus
    -0.63
     Exile
    -0.63
     thereto
    -0.62
    POSITIVE LOGITS
    ris
    1.01
    ounding
    0.98
    oby
    0.97
    resa
    0.96
    arl
    0.96
    itches
    0.96
    aron
    0.94
    arm
    0.94
    anned
    0.94
    rist
    0.93
    Act Density 0.215%

    No Known Activations