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

    Neuronpedia

    INDEX
    Explanations

    actions and changes related to reputation, status, and influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avana
    -0.16
    /Peak
    -0.16
    ighbor
    -0.16
    >NN
    -0.15
    imensional
    -0.15
    oner
    -0.15
     Verfügung
    -0.15
    OLUMN
    -0.14
    oker
    -0.14
    pNet
    -0.14
    POSITIVE LOGITS
    cro
    0.15
    jis
    0.14
     accommodating
    0.14
     overall
    0.14
     Wand
    0.14
    enberg
    0.14
    andle
    0.14
     M
    0.13
    _deinit
    0.13
     Independent
    0.13
    Act Density 0.523%

    No Known Activations