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

    Neuronpedia

    INDEX
    Explanations

    adjectives and phrases associated with describing quality and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ByExample
    -0.20
    cka
    -0.16
    fak
    -0.15
    éŃĤ
    -0.15
    ordova
    -0.15
    éĶ
    -0.14
    ίαÏĤ
    -0.14
    iedy
    -0.14
    æĹĹ
    -0.14
    ">//
    -0.13
    POSITIVE LOGITS
     ,
    0.19
     phen
    0.16
     [=
    0.15
    θη
    0.15
    angan
    0.14
    ames
    0.14
     Wolff
    0.14
     .
    0.14
     instant
    0.14
    uster
    0.14
    Act Density 0.029%

    No Known Activations