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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate significance or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Drv
    -0.14
    ानत
    -0.14
     bam
    -0.14
    ybrid
    -0.14
     Knox
    -0.13
     cash
    -0.13
     Scal
    -0.13
    mdp
    -0.13
     æ©
    -0.13
    oo
    -0.13
    POSITIVE LOGITS
    rzy
    0.17
     move
    0.15
    fak
    0.15
    à¹ģà¸Ķà¸ĩ
    0.14
    ept
    0.14
    acco
    0.14
    iyan
    0.14
    roids
    0.14
    arding
    0.14
    ì¢Ģ
    0.14
    Act Density 0.049%

    No Known Activations