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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by verbs indicating actions.

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and proper nouns indicating specific subjects or agents in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isher
    -0.72
     Amen
    -0.72
     Azerb
    -0.64
    SpaceEngineers
    -0.63
    ormal
    -0.63
    shore
    -0.63
    else
    -0.62
     Else
    -0.60
    north
    -0.60
    imp
    -0.59
    POSITIVE LOGITS
    've
    0.93
    'll
    0.76
    'd
    0.74
     owe
    0.71
    're
    0.71
    self
    0.70
    selves
    0.69
     KNOW
    0.68
    pherd
    0.67
    uristic
    0.65
    Act Density 0.418%

    No Known Activations