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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "said" and similar reporting verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mep
    -0.53
     تانيه
    -0.53
     alone
    -0.51
     Khrushchev
    -0.49
     isso
    -0.48
     Loreto
    -0.47
    ällning
    -0.47
    iseries
    -0.46
    様
    -0.45
     Isso
    -0.45
    POSITIVE LOGITS
    ++]=
    0.83
    — 
    0.82
    ]),
    0.80
     kasarigan
    0.77
    Says
    0.76
    ")));
    0.75
    InjectAttribute
    0.73
    >),
    0.71
    contentLoaded
    0.70
    moiselle
    0.69
    Act Density 0.051%

    No Known Activations