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

    Neuronpedia

    INDEX
    Explanations

    references to changes in statistics or metrics, particularly increases and decreases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    linkplain
    -0.16
    appa
    -0.15
    obble
    -0.14
    VML
    -0.14
     eventual
    -0.14
     Feather
    -0.14
    akes
    -0.14
    owe
    -0.14
    owski
    -0.13
    IMP
    -0.13
    POSITIVE LOGITS
    unft
    0.16
    /update
    0.15
    quals
    0.15
    \Id
    0.15
    oodles
    0.15
    /change
    0.15
    ivet
    0.14
    prung
    0.14
     Wonder
    0.14
    aron
    0.14
    Act Density 0.211%

    No Known Activations