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

    Neuronpedia

    INDEX
    Explanations

    quoted statements or dialogues within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nod
    -0.69
     lair
    -0.66
     nodd
    -0.66
     Versus
    -0.65
     fray
    -0.63
     salute
    -0.60
     playbook
    -0.60
     rundown
    -0.59
     transmitter
    -0.59
     nasal
    -0.58
    POSITIVE LOGITS
    there
    1.28
    nob
    1.23
    everyone
    1.13
    someone
    1.10
    many
    1.08
    they
    1.07
    these
    1.05
    every
    1.01
    few
    0.95
    when
    0.95
    Act Density 0.191%

    No Known Activations