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

    Neuronpedia

    INDEX
    Explanations

    phrases related to instructions or guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yet
    -0.07
     hence
    -0.07
    ,
    -0.06
    eld
    -0.06
     but
    -0.06
     thus
    -0.06
     therefore
    -0.06
     already
    -0.06
    eldon
    -0.06
    yar
    -0.05
    POSITIVE LOGITS
     otherwise
    0.10
     OTHERWISE
    0.10
    otherwise
    0.09
    åIJ¦
    0.09
     Otherwise
    0.09
    Otherwise
    0.09
    uede
    0.08
    меÑĤÑĮ
    0.08
     chances
    0.07
    æ¯ķ
    0.07
    Act Density 0.029%

    No Known Activations