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

    Neuronpedia

    INDEX
    Explanations

    specific characters or patterns in text strings

    oai_token-act-pair · gpt-3.5-turbo

    specific names or references, particularly in connection with music or vocalists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dispatcher
    -0.77
     ancest
    -0.74
     marrow
    -0.71
     roller
    -0.70
     attendant
    -0.69
     runaway
    -0.67
     linkage
    -0.67
     toll
    -0.66
     readiness
    -0.66
     vitro
    -0.65
    POSITIVE LOGITS
    Å¡
    1.23
    Äį
    1.19
    Ëľ
    0.95
    Å
    0.93
    ÃŃn
    0.91
    ι
    0.87
    Ñ
    0.85
    ¾
    0.82
    ÃŃ
    0.82
    ti
    0.81
    Act Density 0.004%

    No Known Activations