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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or hypothetical situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    berdayakan
    -1.12
    ſelves
    -1.10
    ſelf
    -1.06
     cauſe
    -1.04
     itſelf
    -1.04
     Jefus
    -1.01
     pleaſure
    -1.00
     purpoſe
    -1.00
     Efq
    -0.99
     myſelf
    -0.97
    POSITIVE LOGITS
    O
    0.72
     
    0.71
     O
    0.67
    o
    0.66
    N
    0.64
     Z
    0.63
    Z
    0.63
    .
    0.63
    M
    0.62
    B
    0.62
    Act Density 1.168%

    No Known Activations