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

    Neuronpedia

    INDEX
    Explanations

    references to citations or sourced material within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tôt
    -0.59
    떻
    -0.59
    lück
    -0.59
     maux
    -0.58
     ADP
    -0.58
    feats
    -0.57
    cstdlib
    -0.57
     baisse
    -0.57
    Itoa
    -0.56
     организм
    -0.55
    POSITIVE LOGITS
     reference
    3.34
    reference
    2.98
     Reference
    2.94
    Reference
    2.89
     REFERENCE
    2.72
     references
    2.65
    REFERENCE
    2.36
    references
    2.20
     References
    2.19
     referencing
    2.15
    Act Density 0.052%

    No Known Activations