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

    Neuronpedia

    INDEX
    Explanations

    references to names of authors and contributing researchers in academic publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rone
    -0.16
    parator
    -0.15
    pone
    -0.15
    .fs
    -0.15
    pus
    -0.14
    pong
    -0.13
    ienza
    -0.13
    еÑĢÑĸв
    -0.13
    .integration
    -0.13
    dera
    -0.13
    POSITIVE LOGITS
    jev
    0.15
    égor
    0.15
    LTR
    0.15
    ugu
    0.14
    ooth
    0.14
    ves
    0.14
    ibia
    0.14
     Thi
    0.14
    undles
    0.13
    jet
    0.13
    Act Density 0.414%

    No Known Activations