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

    Neuronpedia

    INDEX
    Explanations

    names containing the syllable "abe"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Abe" along with associated terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phis
    -0.99
    matic
    -0.91
    s
    -0.85
    ileaks
    -0.84
    iosity
    -0.82
    ertodd
    -0.82
    prus
    -0.82
    inatory
    -0.81
    achusetts
    -0.81
    nets
    -0.80
    POSITIVE LOGITS
    zza
    1.00
    zzi
    0.92
    zz
    0.90
    ño
    0.88
    ça
    0.83
    ck
    0.81
    lde
    0.81
    legate
    0.78
    cki
    0.77
    utics
    0.77
    Act Density 0.065%

    No Known Activations