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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political figures and events

    oai_token-act-pair · gpt-3.5-turbo

    instances of commas in text, indicating complex sentence structures or lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itar
    -0.71
    Interested
    -0.69
    âĶĢâĶĢâĶĢâĶĢ
    -0.67
    ãĥ¥
    -0.67
    Stra
    -0.60
    ãĥij
    -0.59
    Higher
    -0.59
    board
    -0.59
    ahar
    -0.58
    ¬¼
    -0.57
    POSITIVE LOGITS
     joins
    0.87
     withdrew
    0.84
     nevertheless
    0.81
     understands
    0.74
     testified
    0.74
    zbollah
    0.74
     denies
    0.73
     continues
    0.73
     remembers
    0.72
     believes
    0.72
    Act Density 0.236%

    No Known Activations