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

    Neuronpedia

    INDEX
    Explanations

    the phrase "years ago."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    autant
    -0.71
    last
    -0.63
     letz
    -0.61
     last
    -0.60
    ldt
    -0.57
    las
    -0.57
    тно
    -0.57
    てもら
    -0.57
     Last
    -0.56
    CLOS
    -0.56
    POSITIVE LOGITS
     ago
    1.03
     PGP
    1.02
     AGO
    0.98
     gynhyrchwyd
    0.81
    ]));
    0.78
    CrossRef
    0.77
    homonymie
    0.77
     Lerner
    0.77
     millionaires
    0.75
     Ago
    0.75
    Act Density 0.012%

    No Known Activations