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

    Neuronpedia

    INDEX
    Explanations

    words related to unbreakable or unpenetrable situations or barriers

    oai_token-act-pair · gpt-3.5-turbo

    prefixes and suffixes in words related to barriers, boundaries, or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     initials
    -0.69
    minster
    -0.68
     Patton
    -0.63
     goodbye
    -0.61
     Bans
    -0.61
     boarding
    -0.59
    fork
    -0.58
    spin
    -0.58
     reckoning
    -0.57
    works
    -0.56
    POSITIVE LOGITS
    iture
    1.05
    acy
    1.05
    ibly
    1.04
    iencies
    1.03
    icative
    0.99
    icate
    0.96
    ications
    0.94
    itures
    0.94
    ication
    0.93
    ously
    0.93
    Act Density 0.195%

    No Known Activations