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

    Neuronpedia

    INDEX
    Explanations

    references to drafts and versions of documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bankrupt
    -0.16
    ff
    -0.16
    yo
    -0.14
     gain
    -0.14
     latter
    -0.14
    á»ĩn
    -0.14
    cio
    -0.14
    gain
    -0.14
    arden
    -0.13
    æ¤ħ
    -0.13
    POSITIVE LOGITS
     GOODMAN
    0.17
    rends
    0.16
    ież
    0.16
    ively
    0.16
    ool
    0.15
    _atomic
    0.14
    ishly
    0.14
    Interpreter
    0.14
    ivism
    0.14
     Pru
    0.14
    Act Density 0.013%

    No Known Activations