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

    Neuronpedia

    INDEX
    Explanations

    words related to drugs and their use or effects in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    LayoutStyle
    -0.54
    jsxFileName
    -0.54
     wide
    -0.46
    ']],
    -0.45
     Drit
    -0.45
    })->
    -0.45
    alipay
    -0.44
     jednot
    -0.44
    шње
    -0.43
     choice
    -0.43
    POSITIVE LOGITS
    tvguidetime
    0.75
    
    0.66
    gonic
    0.65
     Италијани
    0.59
    帖最后由
    0.58
    webElementXpaths
    0.58
     fermions
    0.57
     ***!
    0.56
     ferrous
    0.56
    adaptiveStyles
    0.56
    Act Density 0.386%

    No Known Activations