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

    Neuronpedia

    INDEX
    Explanations

    references to internal structures and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     indoors
    -0.74
     indoor
    -0.71
     intracellular
    -0.68
     outdoors
    -0.67
     inland
    -0.60
    indoor
    -0.60
    httphttps
    -0.60
     Indoor
    -0.59
     outdoor
    -0.58
    abestanden
    -0.57
    POSITIVE LOGITS
     workings
    0.76
     monologue
    0.63
     combustion
    0.63
     والخ
    0.58
     diameter
    0.57
     Mongolia
    0.54
     Combustion
    0.54
     Diameter
    0.53
     decorators
    0.52
    halb
    0.51
    Act Density 0.185%

    No Known Activations