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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to measurements or amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mention
    -0.40
    hø
    -0.38
     lead
    -0.38
     Wach
    -0.35
     simply
    -0.35
     namin
    -0.35
    Trabaj
    -0.34
     control
    -0.34
     benzer
    -0.34
     favor
    -0.34
    POSITIVE LOGITS
     المعيارى
    0.84
     esternos
    0.77
    Autoritní
    0.72
    évaluateur
    0.70
    #+#
    0.65
    RTDA
    0.64
     lenker
    0.64
     dAtA
    0.63
    parsedMessage
    0.63
     Administrativna
    0.61
    Act Density 0.486%

    No Known Activations