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

    Neuronpedia

    INDEX
    Explanations

    elements related to financial costs and legal implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Å¡i
    -0.15
     ФедеÑĢалÑĮ
    -0.15
    DonaldTrump
    -0.15
    erp
    -0.15
    lick
    -0.15
     Undo
    -0.14
    icare
    -0.14
    ocator
    -0.14
     pied
    -0.14
    oucher
    -0.14
    POSITIVE LOGITS
     diss
    0.58
     det
    0.47
     deter
    0.45
     Diss
    0.41
    -det
    0.37
     Det
    0.34
    Det
    0.32
    det
    0.32
     discourage
    0.31
     deterrent
    0.31
    Act Density 0.161%

    No Known Activations