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

    Neuronpedia

    INDEX
    Explanations

    words related to relationships and comparisons between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ka
    -0.17
    CSR
    -0.16
    Ø©
    -0.15
    ia
    -0.15
    ant
    -0.15
    ine
    -0.14
    agh
    -0.14
    kova
    -0.14
    uno
    -0.14
     pope
    -0.14
    POSITIVE LOGITS
    ̣
    0.18
    aversable
    0.17
    agate
    0.15
    onian
    0.15
    hots
    0.15
    éĢģæĸĻçĦ¡æĸĻ
    0.15
    eprom
    0.15
    eler
    0.15
    ahoo
    0.14
    iage
    0.14
    Act Density 0.043%

    No Known Activations