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

    Neuronpedia

    INDEX
    Explanations

    names and words containing the syllable "ed"

    oai_token-act-pair · gpt-3.5-turbo

    names and titles related to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.85
    icipated
    -0.76
    kat
    -0.75
    cdn
    -0.75
    PF
    -0.73
    ngth
    -0.68
    drm
    -0.65
    áµ
    -0.65
    hiba
    -0.65
    ":[{"
    -0.65
    POSITIVE LOGITS
    abase
    0.83
     Garland
    0.75
    DonaldTrump
    0.64
    haus
    0.63
    ARD
    0.62
     Louie
    0.61
     Choi
    0.60
     Branch
    0.59
     Eld
    0.59
     Vers
    0.59
    Act Density 0.190%

    No Known Activations