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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating purpose or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.58
    styleType
    -0.53
    uisine
    -0.52
     ModelRenderer
    -0.52
    ifax
    -0.52
    ountain
    -0.51
     BorderRadius
    -0.51
     Possibilities
    -0.51
    LLocation
    -0.50
    desertcart
    -0.50
    POSITIVE LOGITS
     help
    0.54
     כדי
    0.51
     ensure
    0.50
     provide
    0.49
     giúp
    0.48
     nhằm
    0.48
     Comprometido
    0.47
    是为了
    0.47
     забезпе
    0.46
     permitan
    0.44
    Act Density 0.547%

    No Known Activations