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

    Neuronpedia

    INDEX
    Explanations

    negative numerical values, particularly those related to a rating or score system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     חיצוניים
    -0.76
    stylers
    -0.67
    ArrowToggle
    -0.67
    fromnode
    -0.66
     تكبرها
    -0.65
     GeoNames
    -0.65
     Italijanski
    -0.64
     Orrell
    -0.64
    IndentedString
    -0.63
     فريبيس
    -0.63
    POSITIVE LOGITS
    kuuta
    0.60
    trische
    0.51
     BoxFit
    0.51
     
    0.51
    sep
    0.47
    <u>
    0.46
    enumi
    0.46
    bloody
    0.46
    esModule
    0.46
     jButton
    0.45
    Act Density 0.061%

    No Known Activations