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

    Neuronpedia

    INDEX
    Explanations

    non-alphanumeric characters at the end of sentences

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant moments or actions in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mbuds
    -0.65
     endeavor
    -0.58
    arij
    -0.57
     expired
    -0.56
     wound
    -0.56
     intervening
    -0.55
     itching
    -0.55
    cius
    -0.54
     bandits
    -0.54
     inconvenient
    -0.53
    POSITIVE LOGITS
    "(
    0.78
    Narr
    0.78
    Scroll
    0.73
    "
    0.71
    "[
    0.70
     "(
    0.68
    Shape
    0.66
    "'
    0.65
    ""
    0.65
     Pieces
    0.65
    Act Density 0.110%

    No Known Activations