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

    Neuronpedia

    INDEX
    Explanations

    terms associated with significant concepts and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cott
    -0.15
    aucoup
    -0.15
    amba
    -0.15
    aż
    -0.14
    pleasant
    -0.14
    jac
    -0.14
     Transcript
    -0.14
     Cla
    -0.14
    IO
    -0.14
    ami
    -0.14
    POSITIVE LOGITS
     Lob
    0.16
    หย
    0.15
    unist
    0.15
    erta
    0.15
     CrossAxisAlignment
    0.15
     Robbie
    0.14
    á»ĭnh
    0.14
    çĽĸ
    0.14
    ashion
    0.14
    -invalid
    0.13
    Act Density 0.002%

    No Known Activations