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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating progress or timelines related to projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elong
    -0.16
    onde
    -0.16
    arter
    -0.15
    abei
    -0.14
    Pending
    -0.14
    mtree
    -0.14
     پست
    -0.14
    Äħd
    -0.13
    fone
    -0.13
    immune
    -0.13
    POSITIVE LOGITS
     end
    0.75
     beginning
    0.59
     middle
    0.49
     begin
    0.48
    end
    0.47
    -end
    0.46
    .end
    0.45
    begin
    0.45
     END
    0.43
    ,end
    0.42
    Act Density 0.147%

    No Known Activations