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

    Neuronpedia

    INDEX
    Explanations

    patterns of characters such as repeated symbols

    oai_token-act-pair · gpt-3.5-turbo

    sequences of special characters or repeated symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÃĥÃĤ
    -0.66
    unal
    -0.63
    esson
    -0.61
     subur
    -0.61
     exting
    -0.58
    amous
    -0.57
    姫
    -0.56
    Ô
    -0.56
    Ö
    -0.56
    ę
    -0.54
    POSITIVE LOGITS
     apiece
    0.59
     guiActiveUnfocused
    0.58
     blur
    0.56
     GEAR
    0.53
     backlog
    0.52
     spreadsheet
    0.52
     INCLUD
    0.51
     TG
    0.51
     suffice
    0.51
     referee
    0.51
    Act Density 1.742%

    No Known Activations