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

    Neuronpedia

    INDEX
    Explanations

    unique symbols or characters used in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     organising
    -0.20
     organisers
    -0.19
     organised
    -0.18
     ...↵
    -0.18
     ↵
    -0.18
    --↵
    -0.17
    --
    -0.17
     probs
    -0.16
     ...
    -0.16
    aria
    -0.16
    POSITIVE LOGITS
    κη
    0.15
     whereby
    0.14
     pet
    0.14
     rouge
    0.14
     Healthcare
    0.14
    opup
    0.14
    *);↵↵
    0.14
     “âĢ¦
    0.14
    yme
    0.13
     “
    0.13
    Act Density 0.003%

    No Known Activations