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

    Neuronpedia

    INDEX
    Explanations

    the conjunction "And" to identify transitions or connections between different pieces of information

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions that initiate a list or sequence of statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģĨ
    -0.72
    fell
    -0.67
    manship
    -0.65
    sense
    -0.63
    cloth
    -0.63
    ses
    -0.62
    1001
    -0.60
    steam
    -0.60
    sic
    -0.60
    sk
    -0.60
    POSITIVE LOGITS
    rea
    1.37
    romeda
    1.32
    hra
    1.08
    alus
    0.91
    ersen
    0.91
    rogens
    0.88
     secondly
    0.88
    rew
    0.81
    rost
    0.81
    thodox
    0.80
    Act Density 0.064%

    No Known Activations