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

    Neuronpedia

    INDEX
    Explanations

    expressions related to perception and understanding, particularly in social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ery
    -0.17
    ÃĹ</
    -0.15
    plate
    -0.15
    spiel
    -0.15
    illet
    -0.14
    üç
    -0.14
    ookie
    -0.14
    íĸī
    -0.14
    atatype
    -0.14
    STR
    -0.14
    POSITIVE LOGITS
    689
    0.16
    ãĥ³ãĥĦ
    0.15
    OMEM
    0.14
    .githubusercontent
    0.14
    -threat
    0.13
    592
    0.13
    istické
    0.13
     mol
    0.13
     Thur
    0.13
     Crus
    0.13
    Act Density 0.038%

    No Known Activations