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

    Neuronpedia

    INDEX
    Explanations

    data structures and statistical information within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.56
    .
    -0.55
     in
    -0.50
     as
    -0.49
     so
    -0.47
     por
    -0.45
     pro
    -0.44
    ...
    -0.44
    -
    -0.43
     "
    -0.42
    POSITIVE LOGITS
     BoxFit
    1.07
     ſeveral
    0.99
    ंदीखरीदारी
    0.98
     auroit
    0.96
     Majefty
    0.92
    ſelf
    0.90
     Efq
    0.89
     étoient
    0.89
     houſe
    0.89
     avoient
    0.89
    Act Density 0.520%

    No Known Activations