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

    Neuronpedia

    INDEX
    Explanations

    negations and conditions in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.57
     .
    -0.55
     "
    -0.51
    ...
    -0.50
     inoltre
    -0.48
    UnusedPrivate
    -0.48
    fsp
    -0.47
    ?
    -0.47
    :
    -0.47
     donc
    -0.46
    POSITIVE LOGITS
     itſelf
    1.02
     myſelf
    0.97
     $_"
    0.91
     fevere
    0.85
     technically
    0.85
     {},
    0.84
     ſmall
    0.83
     Reſ
    0.83
     fubject
    0.83
     houſe
    0.83
    Act Density 0.319%

    No Known Activations