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

    Neuronpedia

    INDEX
    Explanations

    various forms of human experience and interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.59
     ModelExpression
    -0.56
    rawDesc
    -0.51
    <bos>
    -0.50
    NUMX
    -0.49
     Перейти
    -0.49
    multicolumn
    -0.49
    oltà
    -0.47
    veyard
    -0.47
     bete
    -0.47
    POSITIVE LOGITS
     things
    0.71
    AnchorStyles
    0.67
     surla
    0.66
    indakan
    0.60
     stuff
    0.60
     oneself
    0.59
    things
    0.59
     للاسماء
    0.59
     AssemblyCulture
    0.59
     dingen
    0.58
    Act Density 0.448%

    No Known Activations