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

    Neuronpedia

    INDEX
    Explanations

    indications of examples or subsets related to broader topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unker
    -0.16
     Grü
    -0.15
    isset
    -0.15
    unal
    -0.14
    eyer
    -0.14
    vala
    -0.14
    alls
    -0.14
    रत
    -0.14
    UNK
    -0.13
    oller
    -0.13
    POSITIVE LOGITS
     fraction
    0.26
     mere
    0.25
    åĨ°
    0.24
     merely
    0.24
     tip
    0.24
     iceberg
    0.22
    mere
    0.21
     scratching
    0.21
    -tip
    0.21
    åıªæĺ¯
    0.21
    Act Density 0.127%

    No Known Activations