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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating clarity or obviousness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Marsden
    -0.74
     automatiquement
    -0.73
     BorderRadius
    -0.67
    служба
    -0.64
    #+#
    -0.61
    용
    -0.61
     يتيمه
    -0.60
    euse
    -0.60
    zaine
    -0.59
    Bibliograf
    -0.59
    POSITIVE LOGITS
     clearly
    1.11
    clearly
    1.07
     evident
    1.04
    Clearly
    0.99
     Clearly
    0.98
    VIOUS
    0.95
     obvious
    0.93
     duidelijk
    0.91
    evident
    0.88
    obvious
    0.87
    Act Density 0.160%

    No Known Activations