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

    Neuronpedia

    INDEX
    Explanations

    verbs related to being caught or captured

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "caught."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pronoun
    -0.77
    psey
    -0.75
     livest
    -0.75
     pronouns
    -0.69
     compulsion
    -0.68
    umably
    -0.67
     persuasion
    -0.65
    ankind
    -0.64
    guided
    -0.64
     accents
    -0.63
    POSITIVE LOGITS
    ãĤµ
    0.81
    ãĤ¤ãĥĪ
    0.79
    netflix
    0.74
    cheon
    0.72
     caught
    0.71
     Rai
    0.71
     Luffy
    0.71
    ãĤ¤
    0.70
    ãĤĮ
    0.70
     Tracks
    0.70
    Act Density 0.016%

    No Known Activations