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

    Neuronpedia

    INDEX
    Explanations

    quoted dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Swinger
    -0.18
    gger
    -0.15
    ез
    -0.15
    çģ
    -0.15
    emu
    -0.14
     çŃ
    -0.14
    odon
    -0.14
     compromise
    -0.13
     Feather
    -0.13
    msp
    -0.13
    POSITIVE LOGITS
    uhl
    0.17
    ucz
    0.17
    uchar
    0.16
    AtA
    0.15
     prelim
    0.15
    825
    0.15
     Doch
    0.14
     stripslashes
    0.14
    MethodImpl
    0.14
    quat
    0.14
    Act Density 0.005%

    No Known Activations