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

    Neuronpedia

    INDEX
    Explanations

    adjectives used in hierarchical or confrontational settings

    oai_token-act-pair · gpt-3.5-turbo

    references to political and ideological affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vana
    -0.83
    ndra
    -0.78
    akeru
    -0.75
    nyder
    -0.70
    */(
    -0.70
    aceae
    -0.68
    inki
    -0.68
    agascar
    -0.67
    gger
    -0.64
    ocating
    -0.63
    POSITIVE LOGITS
    INAL
    0.79
    -+-+
    0.78
     Shogun
    0.71
    Ĩ
    0.68
    rontal
    0.67
     Kod
    0.65
    Ö¼
    0.64
     Wad
    0.64
    Bottom
    0.64
    Rect
    0.63
    Act Density 0.376%

    No Known Activations