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

    Neuronpedia

    INDEX
    Explanations

    negative ratings or scores associated with buttons or options

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     utafitiHapana
    -0.67
     LNB
    -0.66
    findpost
    -0.65
    EDEFAULT
    -0.59
     Rake
    -0.59
     tartalomajánló
    -0.59
     ModelExpression
    -0.58
     дописавши
    -0.58
     Vivaldi
    -0.58
    hiker
    -0.58
    POSITIVE LOGITS
     &___
    0.63
    complexType
    0.63
    ssis
    0.57
     @"/
    0.57
    éc
    0.56
    Collegamenti
    0.55
    +".
    0.55
     truth
    0.54
    NullCheck
    0.53
    dus
    0.52
    Act Density 0.005%

    No Known Activations