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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating ease or simplicity

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe ease of action or perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.72
    ONSORED
    -0.72
    lights
    -0.65
    IAL
    -0.65
    orses
    -0.64
    Lim
    -0.63
    minus
    -0.63
    soever
    -0.62
    orp
    -0.60
    ŀ
    -0.59
    POSITIVE LOGITS
     navigate
    0.96
     visualize
    0.94
     assemble
    0.88
     attain
    0.88
     identify
    0.87
     achieve
    0.87
     manipulate
    0.86
     accomplish
    0.85
     digest
    0.85
     confuse
    0.84
    Act Density 0.093%

    No Known Activations