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

    Neuronpedia

    INDEX
    Explanations

    language indicating growth, building relationships, and establishing reputations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    scriptcase
    -0.64
     cessation
    -0.60
    MigrationBuilder
    -0.54
     congi
    -0.53
     Haupts
    -0.53
    cean
    -0.52
     DOW
    -0.51
    рги
    -0.51
    awaiter
    -0.50
    偶
    -0.50
    POSITIVE LOGITS
     reputations
    0.95
     reputation
    0.85
     réputation
    0.84
    UnusedPrivate
    0.78
     reputa
    0.75
    builds
    0.74
    Builds
    0.72
     bygga
    0.72
     buildup
    0.71
     builds
    0.69
    Act Density 0.247%

    No Known Activations