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

    Neuronpedia

    INDEX
    Explanations

    sentences with reported speech

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating reported speech or assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estern
    -0.87
    usk
    -0.70
    umbn
    -0.69
    ocl
    -0.68
    odcast
    -0.65
    iership
    -0.64
    vous
    -0.64
    yna
    -0.64
    emale
    -0.64
    emort
    -0.63
    POSITIVE LOGITS
     "[
    1.10
     instead
    1.00
     "(
    0.96
     that
    0.96
     "'
    0.95
     they
    0.95
     "...
    0.94
     it
    0.93
     ".
    0.89
     therein
    0.86
    Act Density 0.107%

    No Known Activations