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

    Neuronpedia

    INDEX
    Explanations

    references to nodes in a programming or network context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ships
    -0.17
    ½æķ°
    -0.17
    ner
    -0.17
    loaded
    -0.15
    nga
    -0.15
    liÄŁine
    -0.15
    nea
    -0.15
     Bold
    -0.14
    tright
    -0.14
    landers
    -0.14
    POSITIVE LOGITS
    _modules
    0.20
    ules
    0.20
    fault
    0.19
    lete
    0.17
    hood
    0.17
    ktop
    0.16
    FAULT
    0.16
    less
    0.16
    ledge
    0.16
    owner
    0.15
    Act Density 0.076%

    No Known Activations