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

    Neuronpedia

    INDEX
    Explanations

    words related to subterranean or underground contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     inclusive
    -0.65
     reins
    -0.64
     disparate
    -0.64
     fused
    -0.61
     bay
    -0.60
     chained
    -0.60
     trout
    -0.57
     almonds
    -0.57
     silenced
    -0.57
     incurred
    -0.56
    POSITIVE LOGITS
    rible
    1.47
    restrial
    1.41
    ranean
    1.39
    rors
    1.39
    rit
    1.26
    rane
    1.26
    ribly
    1.19
    race
    1.19
    mination
    1.16
    ROR
    1.11
    Act Density 0.005%

    No Known Activations