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

    Neuronpedia

    INDEX
    Explanations

    references to knowledge and understanding, particularly in relation to systems or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lero
    -0.17
    uraa
    -0.17
    ahy
    -0.17
    ÃĸL
    -0.16
     feas
    -0.15
    ENAME
    -0.15
    ertext
    -0.14
     hab
    -0.14
    ylation
    -0.14
    iola
    -0.14
    POSITIVE LOGITS
    .experimental
    0.18
     knows
    0.18
    urgeon
    0.15
     knew
    0.15
     know
    0.15
    çŁ¥éģĵ
    0.15
     Relay
    0.15
    rak
    0.15
     knowledge
    0.14
     already
    0.14
    Act Density 0.124%

    No Known Activations