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

    Neuronpedia

    INDEX
    Explanations

    hyphenated expressions or phrases that involve interruptions or breaks in thought

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     palm
    -0.73
     oven
    -0.73
     mail
    -0.70
     indemn
    -0.69
     mum
    -0.69
     barr
    -0.69
     pronoun
    -0.68
     handic
    -0.68
     swarm
    -0.67
     fid
    -0.67
    POSITIVE LOGITS
    perhaps
    1.41
    meaning
    1.41
    especially
    1.37
    which
    1.36
    including
    1.35
    particularly
    1.35
    that
    1.34
    they
    1.33
    albeit
    1.33
    these
    1.33
    Act Density 0.037%

    No Known Activations