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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating continuity or connection

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "with" indicating companionship or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovich
    -0.65
     Moody
    -0.58
    ynski
    -0.58
    undown
    -0.56
    atoes
    -0.56
     excerpt
    -0.55
    NN
    -0.55
    heimer
    -0.55
     midrange
    -0.55
    borgh
    -0.55
    POSITIVE LOGITS
    stood
    1.27
    drawn
    1.15
     impunity
    1.01
    draw
    1.00
     regard
    0.98
    standing
    0.97
    holding
    0.97
     regards
    0.93
    held
    0.86
     dignity
    0.86
    Act Density 0.158%

    No Known Activations