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

    Neuronpedia

    INDEX
    Explanations

    words related to decision-making processes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to decision-making processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModLoader
    -0.79
     braces
    -0.72
    ragon
    -0.67
     Ell
    -0.65
    auga
    -0.64
    ollar
    -0.64
    ãģ®å®
    -0.63
     Chili
    -0.63
     lux
    -0.62
     bos
    -0.61
    POSITIVE LOGITS
    seeking
    1.15
    related
    1.12
    driven
    1.08
    based
    1.05
    making
    1.02
    packed
    1.02
    management
    1.02
    level
    0.99
    oriented
    0.97
    ridden
    0.96
    Act Density 0.099%

    No Known Activations