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

    Neuronpedia

    INDEX
    Explanations

    statistical data or metrics related to scores or ratings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GLOBALS
    -0.15
    amina
    -0.15
    幸
    -0.15
    ego
    -0.14
     insp
    -0.14
    rend
    -0.14
    ziel
    -0.14
    enor
    -0.14
    hpp
    -0.14
     credential
    -0.13
    POSITIVE LOGITS
    unused
    0.16
    ierre
    0.15
    rier
    0.15
    Evt
    0.14
    loat
    0.14
    акÑģим
    0.14
     reserve
    0.14
    ierge
    0.14
    à¸Ļว
    0.14
    olas
    0.14
    Act Density 0.006%

    No Known Activations