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

    Neuronpedia

    INDEX
    Explanations

    greetings or welcoming messages

    oai_token-act-pair · gpt-3.5-turbo

    the word "As" at the beginning of a statement, indicating a transition or a premise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Carbuncle
    -0.76
     assimil
    -0.70
     reorgan
    -0.67
     mathemat
    -0.65
     absorption
    -0.64
     stren
    -0.64
     tiss
    -0.64
     philos
    -0.63
     extradition
    -0.62
     nep
    -0.62
    POSITIVE LOGITS
    dad
    0.76
    };
    0.69
    762
    0.68
    odes
    0.68
    orum
    0.67
    glers
    0.65
    ede
    0.64
    efe
    0.64
    Todd
    0.63
    ARE
    0.63
    Act Density 0.000%

    No Known Activations