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

    Neuronpedia

    INDEX
    Explanations

    references to scientific citations and publication formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jack
    -0.15
     jack
    -0.15
    ↵↵
    -0.14
    $MESS
    -0.14
    ialog
    -0.14
    gnore
    -0.14
    opol
    -0.14
    ħ§
    -0.14
    ξι
    -0.13
    opsis
    -0.13
    POSITIVE LOGITS
     Sup
    0.22
     suppl
    0.19
    Pt
    0.18
     Pt
    0.18
    Sup
    0.17
     special
    0.16
    orton
    0.16
    oni
    0.16
    _sup
    0.16
     sup
    0.15
    Act Density 0.028%

    No Known Activations