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

    Neuronpedia

    INDEX
    Explanations

    suggestive and indicative phrases that convey insights or conclusions drawn from data or observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loop
    -0.50
    base
    -0.49
    pat
    -0.48
     base
    -0.47
    /
    -0.45
    pase
    -0.44
    BASE
    -0.44
    arat
    -0.44
     
    -0.44
    pa
    -0.43
    POSITIVE LOGITS
    indicates
    1.00
     indicates
    0.95
     Indicates
    0.93
     demuestra
    0.88
     suggests
    0.88
     demonstrates
    0.87
     reflects
    0.87
     indicate
    0.87
    Indicates
    0.86
     testifies
    0.86
    Act Density 0.502%

    No Known Activations