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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "too" and variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ItemBackground
    -0.66
    ly
    -0.65
    mente
    -0.61
    Rhestr
    -0.59
    fully
    -0.58
    ाहरण
    -0.57
     rând
    -0.53
    Controllo
    -0.51
    maßen
    -0.51
    athione
    -0.51
    POSITIVE LOGITS
    thy
    0.84
     late
    0.74
     much
    0.73
     soon
    0.68
     many
    0.63
    ths
    0.62
     early
    0.58
    led
    0.57
    Much
    0.56
     busy
    0.56
    Act Density 0.053%

    No Known Activations