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

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    pronouns used in a context of human interactions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bold
    -0.67
     Forth
    -0.60
    ono
    -0.60
    ;;;;;;;;;;;;
    -0.59
    00200000
    -0.59
     Consortium
    -0.58
    scrib
    -0.57
    oud
    -0.57
    pathic
    -0.57
     Amen
    -0.57
    POSITIVE LOGITS
     arrived
    0.81
     came
    0.78
     transitioned
    0.76
     introduced
    0.75
     toured
    0.74
     slightest
    0.72
     ventured
    0.71
     began
    0.71
     confronted
    0.70
     asked
    0.69
    Act Density 0.153%

    No Known Activations