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

    Neuronpedia

    INDEX
    Explanations

    concepts related to iterative processes and feedback loops

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ols
    -0.15
    chner
    -0.15
     Fare
    -0.14
    ÑĢаг
    -0.14
     irreversible
    -0.14
    angler
    -0.14
    amak
    -0.13
    iph
    -0.13
    YS
    -0.13
    pit
    -0.13
    POSITIVE LOGITS
     repeat
    0.56
    Repeat
    0.50
    repeat
    0.49
     Repeat
    0.49
     repeats
    0.48
     repeating
    0.43
    -repeat
    0.39
     repetition
    0.38
     repeated
    0.38
    _repeat
    0.34
    Act Density 0.117%

    No Known Activations