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

    Neuronpedia

    INDEX
    Explanations

    words related to attraction or persuasion

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ent."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    士
    -0.67
     Spears
    -0.65
     inclusive
    -0.61
    phrine
    -0.61
     overdue
    -0.60
    BILITIES
    -0.59
    Ø©
    -0.59
    aneers
    -0.58
     Scotia
    -0.58
    ned
    -0.58
    POSITIVE LOGITS
    ourage
    1.18
    ailed
    1.11
    rench
    1.10
    renched
    1.08
    rust
    1.02
    repre
    1.02
    rance
    1.02
    ropy
    1.02
    race
    0.99
    rained
    0.96
    Act Density 0.027%

    No Known Activations