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

    Neuronpedia

    INDEX
    Explanations

    closing brackets and punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    egin
    -0.19
    ied
    -0.16
     lud
    -0.15
    оÑıÑĤ
    -0.14
    -option
    -0.14
    ody
    -0.14
     detach
    -0.14
    ford
    -0.14
    AffineTransform
    -0.14
     Karlov
    -0.14
    POSITIVE LOGITS
    ÌĢ
    0.15
    endance
    0.14
    ulin
    0.14
    FM
    0.14
    hl
    0.14
    ican
    0.14
    JC
    0.14
    éľ
    0.14
     concession
    0.14
     concessions
    0.13
    Act Density 0.020%

    No Known Activations