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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate intention or action towards achieving something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prominently
    -0.68
     Shant
    -0.68
     curiously
    -0.62
     todd
    -0.61
     tumble
    -0.56
     blush
    -0.55
     concess
    -0.55
     ANGEL
    -0.55
     palp
    -0.54
     Electronic
    -0.54
    POSITIVE LOGITS
     death
    0.83
    ths
    0.73
    inas
    0.70
    ãĤ¢
    0.69
    Contents
    0.68
    justice
    0.66
    deg
    0.66
    Death
    0.65
    ãĥ©ãĥ³
    0.65
    yrights
    0.64
    Act Density 0.605%

    No Known Activations