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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of improvement or progress

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "with" indicating relationships or associations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obook
    -0.66
    mart
    -0.64
     âĢİ
    -0.59
     ALSO
    -0.59
    chuk
    -0.58
    ovich
    -0.58
    handler
    -0.57
     /*
    -0.57
     Establishment
    -0.55
    hops
    -0.55
    POSITIVE LOGITS
     regards
    1.62
     regard
    1.61
    stood
    1.39
    standing
    1.26
    draw
    1.22
     respect
    1.19
     impunity
    1.15
    drawn
    1.11
    holding
    1.02
     dignity
    0.84
    Act Density 0.230%

    No Known Activations