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

    Neuronpedia

    INDEX
    Explanations

    references or citations embedded in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to lists or enumerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     neigh
    -0.75
    atts
    -0.74
    uca
    -0.71
    udes
    -0.69
    inelli
    -0.69
    uters
    -0.67
    umbers
    -0.65
    mens
    -0.65
    racuse
    -0.65
     answer
    -0.65
    POSITIVE LOGITS
    Appearances
    1.11
    References
    1.09
    Notable
    1.02
    However
    1.01
    Synopsis
    1.00
    Contents
    0.97
    Appearance
    0.96
    Characters
    0.96
    Later
    0.95
    Gameplay
    0.94
    Act Density 0.107%

    No Known Activations