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

    Neuronpedia

    INDEX
    Explanations

    language indicating uncertainty or variability in perspectives and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocities
    -0.16
    icari
    -0.16
    isclosed
    -0.16
    osphere
    -0.16
    afen
    -0.15
    าà¸ĩ
    -0.15
    artin
    -0.15
    çŃ
    -0.14
     Barrier
    -0.14
    ombies
    -0.14
    POSITIVE LOGITS
     segment
    0.16
    mer
    0.14
     Segment
    0.14
     Tes
    0.14
    ody
    0.14
    ignet
    0.14
     merg
    0.14
     Flooring
    0.14
     sed
    0.14
     tes
    0.13
    Act Density 0.148%

    No Known Activations