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

    Neuronpedia

    INDEX
    Explanations

    prepositions and conjunctions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate comparisons or relationships between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ":-
    -0.75
    ses
    -0.75
    @@
    -0.66
    .",
    -0.65
    .:
    -0.63
    Sep
    -0.60
    usercontent
    -0.60
     (?,
    -0.60
    ciplinary
    -0.59
     '/
    -0.59
    POSITIVE LOGITS
     incidentally
    0.87
    ardless
    0.82
     spoiler
    0.76
    theless
    0.76
    arently
    0.75
     ironically
    0.72
    !)
    0.70
    lihood
    0.69
    -)
    0.69
    !).
    0.67
    Act Density 0.329%

    No Known Activations