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

    Neuronpedia

    INDEX
    Explanations

    phrases related to comparison or analysis

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey a sense of improvement or gaining understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sbm
    -0.87
    theless
    -0.70
    Lago
    -0.68
     Spons
    -0.67
    FML
    -0.66
    rous
    -0.64
     stunts
    -0.64
     sacrifices
    -0.63
    die
    -0.63
    BAT
    -0.62
    POSITIVE LOGITS
     insight
    1.36
     idea
    1.34
     indication
    1.33
     sense
    1.33
     clue
    1.27
     glimpse
    1.24
     grasp
    1.21
     picture
    1.19
     impression
    1.18
     understanding
    1.18
    Act Density 0.218%

    No Known Activations