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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate uncertainty or lack of consensus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    venir
    -0.17
    ories
    -0.14
    pons
    -0.13
     shit
    -0.13
    flies
    -0.13
    leness
    -0.13
    ACHINE
    -0.13
    TMP
    -0.13
    ÚĨÙĩ
    -0.12
    /Resources
    -0.12
    POSITIVE LOGITS
     except
    0.18
    except
    0.16
     Except
    0.16
    owl
    0.15
    Except
    0.15
    iem
    0.14
    inyin
    0.14
     anywhere
    0.14
     Lloyd
    0.14
    plx
    0.14
    Act Density 0.126%

    No Known Activations