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

    Neuronpedia

    INDEX
    Explanations

    terms related to social interactions and friendship connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ypes
    -0.17
    ç«ł
    -0.16
     Nah
    -0.15
    stery
    -0.15
    utton
    -0.15
    kea
    -0.15
    yny
    -0.14
    itol
    -0.14
    stral
    -0.14
    mere
    -0.13
    POSITIVE LOGITS
    adder
    0.17
    reck
    0.16
    aggi
    0.16
     whom
    0.16
    /conf
    0.14
     separator
    0.14
     fellow
    0.13
    ÅĻÃŃz
    0.13
     PAN
    0.13
    oard
    0.13
    Act Density 0.029%

    No Known Activations