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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦
    -0.61
    æĺ¯
    -0.55
     Entered
    -0.54
     plateau
    -0.54
    ¥µ
    -0.54
    EPA
    -0.53
     ``(
    -0.53
     âĶľâĶĢâĶĢ
    -0.53
    ":"","
    -0.53
    states
    -0.53
    POSITIVE LOGITS
     alive
    0.89
     overboard
    0.82
    's
    0.81
     onto
    0.79
     accountable
    0.77
     ineligible
    0.77
     hostage
    0.75
    ieri
    0.73
     away
    0.71
     into
    0.71
    Act Density 0.386%

    No Known Activations