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

    Neuronpedia

    INDEX
    Explanations

    instances of feedback loops and iterative processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Martins
    -0.16
    ols
    -0.15
    ĥĿ
    -0.14
    ackbar
    -0.14
    lla
    -0.14
     Turks
    -0.14
    tsx
    -0.14
     Fare
    -0.13
    å
    -0.13
     mol
    -0.13
    POSITIVE LOGITS
     etc
    0.43
    etc
    0.39
    /etc
    0.23
     atd
    0.23
    å¦ĤæѤ
    0.22
    çŃī
    0.22
     ÑĤоÑīо
    0.22
    repeat
    0.22
     cycle
    0.21
     continue
    0.21
    Act Density 0.085%

    No Known Activations