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

    Neuronpedia

    INDEX
    Explanations

    references to things that are clearly evident or easily understood

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lings
    -0.16
    UPPORTED
    -0.15
    볨
    -0.15
    abilit
    -0.15
     whole
    -0.15
    atted
    -0.14
    actable
    -0.14
    istrovstvÃŃ
    -0.14
    ülebilir
    -0.14
    lein
    -0.14
    POSITIVE LOGITS
    mente
    0.18
    çĦ¶
    0.17
    ely
    0.16
    arent
    0.15
    ly
    0.15
    ugins
    0.15
    ness
    0.14
    cob
    0.14
    376
    0.14
    ivec
    0.14
    Act Density 0.032%

    No Known Activations