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

    Neuronpedia

    INDEX
    Explanations

    phrases related to events, locations, and people

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "with" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cemic
    -0.62
    pad
    -0.61
    press
    -0.60
    axy
    -0.60
    fair
    -0.59
    strap
    -0.58
    soft
    -0.58
    hops
    -0.58
    bilt
    -0.57
    winter
    -0.57
    POSITIVE LOGITS
    stood
    1.43
     regards
    1.41
     regard
    1.40
    draw
    1.29
    standing
    1.17
    drawn
    1.16
     impunity
    1.11
     respect
    1.07
    holding
    1.01
     dignity
    0.79
    Act Density 0.266%

    No Known Activations