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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making statements or clarifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.51
    hastly
    -0.48
     ?>>
    -0.47
    etary
    -0.45
     present
    -0.45
     physical
    -0.45
     pinulongan
    -0.45
    ENGER
    -0.45
    OWSKI
    -0.44
    joh
    -0.44
    POSITIVE LOGITS
     disparu
    0.64
    SizeF
    0.62
     iprot
    0.61
     <>",
    0.61
     Negroes
    0.60
     umane
    0.59
    +#+#
    0.59
    WindowConstants
    0.58
     voici
    0.57
     quitté
    0.57
    Act Density 0.167%

    No Known Activations