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

    Neuronpedia

    INDEX
    Explanations

    verbs related to the concept of change or improvement

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "revive" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Story
    -0.76
     charism
    -0.73
    Fine
    -0.64
    JUST
    -0.63
     Tale
    -0.62
     Highlander
    -0.62
     Crate
    -0.62
    lehem
    -0.61
    女
    -0.61
     Tribe
    -0.60
    POSITIVE LOGITS
    ulsion
    1.20
    ivals
    1.18
    ascular
    1.17
    olved
    1.15
    olve
    1.08
    amping
    1.08
    iving
    1.01
    isions
    0.99
    ulsive
    0.99
    oking
    0.98
    Act Density 0.018%

    No Known Activations