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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing a degree or comparison

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and phrases indicating degrees of severity or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udder
    -0.80
    vier
    -0.75
    acus
    -0.74
     Lastly
    -0.73
    hots
    -0.72
    someone
    -0.69
    utics
    -0.68
    Desk
    -0.68
    eva
    -0.67
    _-
    -0.67
    POSITIVE LOGITS
     nature
    1.52
    ness
    1.30
     ramifications
    1.25
     implications
    1.19
     importance
    1.18
     workings
    1.18
     complexities
    1.16
     prevalence
    1.14
     effects
    1.12
     consequences
    1.11
    Act Density 0.275%

    No Known Activations