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

    Neuronpedia

    INDEX
    Explanations

    alphanumeric strings and identifiers often seen in code or structured data formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſtate
    -0.90
     itſelf
    -0.89
     poffe
    -0.87
     pleaſure
    -0.83
     faſt
    -0.83
     newOwner
    -0.81
     houſe
    -0.79
     ftate
    -0.79
     doubtnut
    -0.79
     iſt
    -0.78
    POSITIVE LOGITS
    p
    0.56
    StoreMessageInfo
    0.52
     Dan
    0.51
     bắc
    0.51
    mu
    0.50
    comp
    0.50
     A
    0.50
     p
    0.49
    Chor
    0.48
    かが
    0.48
    Act Density 0.011%

    No Known Activations