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

    Neuronpedia

    INDEX
    Explanations

    phrases or patterns related to evaluation and comparison of entities or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fern
    -0.16
    ará
    -0.14
    quare
    -0.14
    arters
    -0.14
    imo
    -0.14
    ylon
    -0.14
    hta
    -0.14
    ombat
    -0.14
    ud
    -0.13
    avian
    -0.13
    POSITIVE LOGITS
     ways
    0.23
     Ways
    0.17
    象
    0.15
     Nimbus
    0.15
    oulos
    0.14
     gì
    0.14
    633
    0.14
    NSE
    0.14
    axis
    0.14
    å©·
    0.14
    Act Density 0.032%

    No Known Activations