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

    Neuronpedia

    INDEX
    Explanations

    function words that indicate relationships and connections in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igth
    -0.16
    cales
    -0.15
    IXEL
    -0.15
    ledo
    -0.14
    cov
    -0.14
    roz
    -0.14
    gnore
    -0.14
    ubs
    -0.14
     اÙĦعÙħ
    -0.13
    roti
    -0.13
    POSITIVE LOGITS
     mus
    0.17
    uki
    0.16
    452
    0.15
    .mit
    0.15
    402
    0.15
     ext
    0.15
     Merry
    0.15
    اساÙĨ
    0.15
    mpp
    0.15
    çĤī
    0.14
    Act Density 0.036%

    No Known Activations