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

    Neuronpedia

    INDEX
    Explanations

    phrases related to evaluating statements or actions

    oai_token-act-pair · gpt-3.5-turbo

    statements emphasizing the concept of health and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     notices
    -0.68
     senses
    -0.65
     Naj
    -0.65
     Prosper
    -0.63
     floats
    -0.62
     peg
    -0.62
     fares
    -0.62
     Vald
    -0.60
     Maced
    -0.60
     orbits
    -0.60
    POSITIVE LOGITS
    senal
    1.04
    rael
    0.91
     definitely
    0.88
     indeed
    0.83
     akin
    0.83
     certainly
    0.83
    ŃĶ
    0.82
    olate
    0.82
     therefore
    0.81
     nevertheless
    0.80
    Act Density 0.327%

    No Known Activations