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

    Neuronpedia

    INDEX
    Explanations

    topics related to various groups of people and their interactions or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bis
    -0.15
    ctxt
    -0.15
    ulla
    -0.15
    unts
    -0.14
    lı
    -0.14
    rát
    -0.14
     barg
    -0.14
    ãĥĥãĤ°
    -0.14
    late
    -0.13
    roach
    -0.13
    POSITIVE LOGITS
     everywhere
    0.77
     Everywhere
    0.49
     worldwide
    0.40
     across
    0.40
     nationwide
    0.36
     throughout
    0.35
     anywhere
    0.30
     alike
    0.28
    Across
    0.27
     Across
    0.27
    Act Density 0.220%

    No Known Activations