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

    Neuronpedia

    INDEX
    Explanations

    instances where the text discusses or encourages participation in various activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "participate" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thur
    -0.71
    flies
    -0.69
    cut
    -0.63
    fly
    -0.63
    forward
    -0.62
    flu
    -0.62
    pex
    -0.62
    borne
    -0.61
    ASC
    -0.61
    headed
    -0.61
    POSITIVE LOGITS
    ivity
    0.86
     Participation
    0.74
    ucky
    0.71
    udo
    0.70
     participates
    0.70
     participate
    0.70
     guiActiveUn
    0.69
    Spons
    0.69
    nels
    0.69
    ACTION
    0.69
    Act Density 0.024%

    No Known Activations