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

    Neuronpedia

    INDEX
    Explanations

    fragments of conversations or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Inbox
    -0.16
    uÄį
    -0.15
    ark
    -0.15
     MPI
    -0.15
    697
    -0.15
    Unsafe
    -0.14
     --
    -0.14
    utes
    -0.14
     Riley
    -0.13
     Burnett
    -0.13
    POSITIVE LOGITS
    leon
    0.18
     æ¢
    0.15
    ÑıÑħ
    0.15
     vend
    0.15
     konkrét
    0.15
     ìĿµ
    0.15
    INY
    0.14
    avra
    0.14
    lisi
    0.14
    EndInit
    0.13
    Act Density 0.042%

    No Known Activations