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

    Neuronpedia

    INDEX
    Explanations

    prefixes related to "con" and "in" root words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rok
    -0.15
    amoto
    -0.14
    ired
    -0.14
    arl
    -0.14
    pawn
    -0.14
     mÃŃ
    -0.14
    ĨĴ
    -0.14
    aska
    -0.14
     SNAP
    -0.14
    ence
    -0.14
    POSITIVE LOGITS
    olley
    0.20
    radi
    0.19
    olly
    0.19
    jug
    0.19
    ÏĥÏĦαν
    0.18
    nelly
    0.17
    igli
    0.17
    iglia
    0.17
    tra
    0.17
    duit
    0.16
    Act Density 0.064%

    No Known Activations