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

    Neuronpedia

    INDEX
    Explanations

    references to ways of doing things and exploring methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ikip
    -0.15
    inherits
    -0.14
    effect
    -0.14
     ÑĦак
    -0.14
    enia
    -0.13
    ILLE
    -0.13
    ickey
    -0.13
     å¹
    -0.13
    ught
    -0.13
    tring
    -0.13
    POSITIVE LOGITS
     ways
    0.65
     Ways
    0.47
    ways
    0.44
     way
    0.43
    WAYS
    0.32
    eways
    0.31
    .way
    0.29
    way
    0.29
     sposób
    0.28
     manera
    0.28
    Act Density 0.138%

    No Known Activations