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

    Neuronpedia

    INDEX
    Explanations

    phrases or references related to guidance or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iw
    -0.16
     Bowen
    -0.15
    rg
    -0.15
    FFE
    -0.15
    _bn
    -0.14
    loff
    -0.14
    ij
    -0.14
    kowski
    -0.14
    .masks
    -0.14
    اÙĩÛĮ
    -0.14
    POSITIVE LOGITS
    esteem
    0.15
    Õ¡
    0.14
    orig
    0.14
    enaire
    0.14
    ëĦ¤
    0.14
    *pi
    0.14
    izz
    0.14
    âĤĢ
    0.14
    ãĥ©ãĤ¯
    0.13
    293
    0.13
    Act Density 0.020%

    No Known Activations