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

    Neuronpedia

    INDEX
    Explanations

    references to uniqueness or similarity in types or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hev
    -0.17
    794
    -0.17
    antu
    -0.15
    lob
    -0.15
    ìłĿ
    -0.15
    069
    -0.14
     Crosby
    -0.14
    andle
    -0.14
    sb
    -0.14
    049
    -0.14
    POSITIVE LOGITS
    TF
    0.16
    elo
    0.15
    fx
    0.15
    оза
    0.14
    bulk
    0.14
    ách
    0.14
    ores
    0.14
    fp
    0.14
    wert
    0.14
     Wyatt
    0.14
    Act Density 0.298%

    No Known Activations