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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word "with" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etten
    -0.16
    uren
    -0.15
    acle
    -0.14
    prit
    -0.14
    haps
    -0.13
    еÑĢÑĤи
    -0.13
    devil
    -0.13
    hoff
    -0.13
    à¸Ńà¸ĩà¸Īาà¸ģ
    -0.13
    enen
    -0.13
    POSITIVE LOGITS
    stood
    0.30
     regard
    0.29
     regards
    0.28
    standing
    0.26
     nhau
    0.24
    /by
    0.24
     respect
    0.22
    drawing
    0.22
    holds
    0.20
    lac
    0.18
    Act Density 0.509%

    No Known Activations