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

    Neuronpedia

    INDEX
    Explanations

    collaborative language and themes related to teamwork

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     '
    -0.17
     –
    -0.16
     Anything
    -0.15
    centre
    -0.15
     --
    -0.14
    çļĦä¸Ģ个
    -0.14
     ...
    -0.14
    oup
    -0.14
     -
    -0.13
    today
    -0.13
    POSITIVE LOGITS
     wiÄĻc
    0.14
    érc
    0.14
    emp
    0.14
     comb
    0.13
    GRES
    0.13
     disc
    0.13
    658
    0.12
    ÂŃtion
    0.12
     ì§ģ
    0.12
     recru
    0.12
    Act Density 0.521%

    No Known Activations