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

    Neuronpedia

    INDEX
    Explanations

    words related to complex descriptions or evaluations of situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pel
    -0.15
    orage
    -0.15
    fq
    -0.14
    Pel
    -0.14
    zd
    -0.14
     THR
    -0.14
    zi
    -0.14
    iqu
    -0.14
     Ramp
    -0.14
     Shia
    -0.14
    POSITIVE LOGITS
    _mD
    0.16
    ersen
    0.16
    stell
    0.15
     pou
    0.15
    kami
    0.14
    edis
    0.14
    ÏģÏį
    0.14
    _mC
    0.13
    irth
    0.13
    overn
    0.13
    Act Density 0.011%

    No Known Activations