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

    Neuronpedia

    INDEX
    Explanations

    phrases related to things that are continual, never-ending, or without a clear endpoint

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "endless" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acus
    -0.91
    Reviewed
    -0.80
    iquette
    -0.80
    akers
    -0.79
    illard
    -0.79
    PI
    -0.76
    atche
    -0.73
    acist
    -0.71
    dor
    -0.69
    mast
    -0.69
    POSITIVE LOGITS
     repetition
    0.91
     regress
    0.83
     loop
    0.79
    ãĥ©ãĥ³
    0.79
     gratification
    0.76
     repet
    0.76
     replay
    0.76
     tort
    0.74
     succession
    0.74
     plains
    0.73
    Act Density 0.021%

    No Known Activations