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

    Neuronpedia

    INDEX
    Explanations

    syntactical structures and morphological forms in language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     absol
    -0.16
     éĹ
    -0.16
    egra
    -0.15
     å¯Į
    -0.14
    avenport
    -0.14
    aved
    -0.14
    áv
    -0.14
    Mismatch
    -0.14
    azard
    -0.14
    urum
    -0.13
    POSITIVE LOGITS
     veloc
    0.23
     rapid
    0.21
     da
    0.21
     ug
    0.21
     gradual
    0.21
     dap
    0.20
     nu
    0.20
     nett
    0.20
     age
    0.20
     pure
    0.20
    Act Density 0.010%

    No Known Activations