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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a lack of evidence or proof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aoke
    -0.15
    olg
    -0.15
    ething
    -0.15
     somewhat
    -0.15
    .AutoScaleMode
    -0.15
    ardless
    -0.14
    angan
    -0.14
     hors
    -0.14
    stered
    -0.13
    RID
    -0.13
    POSITIVE LOGITS
    except
    0.19
     except
    0.19
    Except
    0.18
     кÑĢоме
    0.17
    _except
    0.17
     Except
    0.16
    503
    0.15
    essen
    0.15
    polator
    0.15
     Matter
    0.14
    Act Density 0.261%

    No Known Activations