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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "cla" followed by other letters, indicating a focus on words starting with that sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ruba
    -0.17
    il
    -0.17
    ban
    -0.16
    atee
    -0.16
    iliz
    -0.15
    frey
    -0.15
     aging
    -0.14
    ÛĮÙĦÛĮ
    -0.14
    足
    -0.14
     banquet
    -0.14
    POSITIVE LOGITS
    esson
    0.29
    ussen
    0.28
    assen
    0.26
    udio
    0.22
    ire
    0.22
    ude
    0.22
    ifornia
    0.20
    IRE
    0.20
    essen
    0.19
    ques
    0.19
    Act Density 0.005%

    No Known Activations