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

    Neuronpedia

    INDEX
    Explanations

    court case citations

    oai_token-act-pair · gpt-3.5-turbo

    legal case citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bsite
    -0.71
    ptoms
    -0.68
     cleaner
    -0.63
     liner
    -0.63
    accessible
    -0.62
     ingredients
    -0.62
     ingredient
    -0.61
    colour
    -0.61
    phia
    -0.60
    cheat
    -0.58
    POSITIVE LOGITS
    arsity
    0.83
    isions
    0.82
    iii
    0.78
    iking
    0.77
    Sphere
    0.74
    ented
    0.74
    iper
    0.73
    igg
    0.73
    incent
    0.73
    iably
    0.72
    Act Density 0.015%

    No Known Activations