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

    Neuronpedia

    INDEX
    Explanations

    words related to definitions or explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fork
    -0.08
    AtPath
    -0.08
    bread
    -0.07
    faction
    -0.07
    ledge
    -0.07
    íĭ±
    -0.07
    殿
    -0.07
    armac
    -0.07
    fac
    -0.07
    eros
    -0.07
    POSITIVE LOGITS
    initely
    0.08
     def
    0.07
     Def
    0.07
    -def
    0.07
    rock
    0.07
    nable
    0.07
     horn
    0.07
    nar
    0.06
    (def
    0.06
     namedtuple
    0.06
    Act Density 0.031%

    No Known Activations