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

    Neuronpedia

    INDEX
    Explanations

    elements related to character roles and their dynamics in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.77
     מאוד
    -0.59
     verschill
    -0.56
     Juifs
    -0.54
     greatly
    -0.53
     délib
    -0.52
     vanske
    -0.52
     separately
    -0.52
     geweest
    -0.50
     modalités
    -0.50
    POSITIVE LOGITS
     complete
    0.98
    complete
    0.97
     replete
    0.82
     Complete
    0.82
     COMPLETE
    0.81
    Complete
    0.80
     courtesy
    0.77
     circa
    0.77
    courtesy
    0.73
     clutching
    0.70
    Act Density 0.706%

    No Known Activations