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

    Neuronpedia

    INDEX
    Explanations

    instances of encounters with varying contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "encounter" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aku
    -0.86
    roxy
    -0.82
    actor
    -0.80
    direction
    -0.80
    elled
    -0.73
    chen
    -0.70
    estate
    -0.69
    riger
    -0.69
    solid
    -0.69
    cott
    -0.68
    POSITIVE LOGITS
    ãĥķ
    0.91
     encounters
    0.80
     encountered
    0.80
    ttes
    0.79
     Garc
    0.79
     Wander
    0.74
     Metatron
    0.73
    ually
    0.72
    ãĤ¼
    0.70
     encounter
    0.69
    Act Density 0.015%

    No Known Activations