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

    Neuronpedia

    INDEX
    Explanations

    phrases ending in certain punctuation marks, particularly

    oai_token-act-pair · gpt-3.5-turbo

    unique textual markers or special formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eleph
    -0.76
     tradem
    -0.75
     reper
    -0.72
     estranged
    -0.69
     amnesty
    -0.67
     theirs
    -0.67
     interven
    -0.66
     deposit
    -0.65
     withdrawal
    -0.64
     destro
    -0.64
    POSITIVE LOGITS
    WASHINGTON
    1.16
    CLOSE
    1.15
    Still
    1.11
    Abstract
    1.08
    Untitled
    1.05
    Trivia
    1.05
    Description
    1.04
    Overview
    1.04
    Breaking
    1.02
    Quote
    1.02
    Act Density 0.096%

    No Known Activations