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

    Neuronpedia

    INDEX
    Explanations

    references to attachment or connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jte
    -0.17
    à¹īà¸ĩ
    -0.15
    jing
    -0.15
    naments
    -0.14
    å¹ķ
    -0.14
    stras
    -0.14
    naire
    -0.14
     STDERR
    -0.14
    oreach
    -0.13
    stown
    -0.13
    POSITIVE LOGITS
    endum
    0.18
    /embed
    0.16
    iline
    0.16
    itude
    0.16
    olicy
    0.15
    ories
    0.15
    sel
    0.15
    oll
    0.15
    .createStatement
    0.15
    -sama
    0.14
    Act Density 0.025%

    No Known Activations