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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating incomplete or stalled projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ãĤŃãĥ£
    -0.16
    astos
    -0.15
    ertain
    -0.15
    ernet
    -0.14
    åĸ
    -0.14
    atern
    -0.14
    tir
    -0.13
     reverse
    -0.13
    irect
    -0.13
     organ
    -0.13
    POSITIVE LOGITS
     delay
    0.20
     delays
    0.18
     promised
    0.17
     Delay
    0.17
    538
    0.17
     Lim
    0.16
    LAG
    0.16
     progress
    0.16
     until
    0.16
     lim
    0.16
    Act Density 0.181%

    No Known Activations