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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of attaching or fastening objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sesso
    -0.16
    ongan
    -0.16
    buzz
    -0.16
     DropIndex
    -0.15
    .au
    -0.15
    NEY
    -0.15
    isher
    -0.15
     BS
    -0.15
     пÑĢиз
    -0.15
    edList
    -0.14
    POSITIVE LOGITS
     Attach
    0.16
    uy
    0.16
     underlying
    0.14
    ائÙĤ
    0.14
     attached
    0.14
    æĸŃ
    0.14
    ment
    0.13
    IRD
    0.13
    èĻķ
    0.13
    ments
    0.13
    Act Density 0.009%

    No Known Activations