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

    Neuronpedia

    INDEX
    Explanations

    references to television shows and productions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ocab
    -0.17
    Linked
    -0.15
    felt
    -0.14
     kot
    -0.14
    ADM
    -0.14
    itored
    -0.13
     courtesy
    -0.13
    润
    -0.13
    romium
    -0.13
    158
    -0.13
    POSITIVE LOGITS
    Written
    0.23
     Written
    0.21
     written
    0.21
    written
    0.20
     meant
    0.16
    anko
    0.16
    -written
    0.15
    ESH
    0.15
     sung
    0.15
     Tail
    0.14
    Act Density 0.030%

    No Known Activations