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

    Neuronpedia

    INDEX
    Explanations

    definitions or meanings of words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    JP
    -0.85
    の�
    -0.81
    jpg
    -0.77
     ILCS
    -0.77
    RF
    -0.76
    Nat
    -0.74
    TF
    -0.73
    王
    -0.73
    VK
    -0.72
    �
    -0.72
    POSITIVE LOGITS
     chopping
    0.72
     prey
    0.70
     finish
    0.69
     answering
    0.69
     ridden
    0.68
     laun
    0.67
     defense
    0.67
     batter
    0.67
     takeover
    0.67
     lodging
    0.66
    Act Density 0.024%

    No Known Activations