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

    Neuronpedia

    INDEX
    Explanations

    positive words or expressions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of positivity and positive sentiment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loo
    -0.84
     Brilliant
    -0.71
    HAEL
    -0.70
    opsy
    -0.70
    Leod
    -0.68
    tracks
    -0.68
    wine
    -0.66
     Hearts
    -0.63
     Recall
    -0.62
    stall
    -0.62
    POSITIVE LOGITS
    itional
    1.51
    itions
    1.34
    itivity
    1.26
    idon
    1.15
    itionally
    1.13
    itory
    1.10
    itiveness
    1.07
    itor
    1.06
    ited
    1.04
    icion
    1.03
    Act Density 0.029%

    No Known Activations