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

    Neuronpedia

    INDEX
    Explanations

    instances of "including" and related words, indicating a focus on inclusivity or enumerative listing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     houſe
    -0.84
     purpoſe
    -0.76
     ſche
    -0.70
     ſtate
    -0.69
     ?...
    -0.68
     greateſt
    -0.67
     Efq
    -0.67
     fubject
    -0.67
     whoſe
    -0.66
     ſhe
    -0.66
    POSITIVE LOGITS
     including
    0.85
     those
    0.77
    INCLUDING
    0.76
    including
    0.73
     Including
    0.73
     waaronder
    0.71
     ones
    0.69
     the
    0.69
    Including
    0.67
     INCLUDING
    0.67
    Act Density 0.163%

    No Known Activations