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

    Neuronpedia

    INDEX
    Explanations

    terms related to saliency in visual content and configuration settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.36
     Theſe
    -1.19
     myſelf
    -1.17
     theſe
    -1.16
     Monfieur
    -1.15
     Houſe
    -1.14
     iſt
    -1.10
     houſe
    -1.10
     faſt
    -1.10
     purpoſe
    -1.08
    POSITIVE LOGITS
     Ra
    0.96
     Sw
    0.96
     Qu
    0.94
     Ar
    0.94
     Ste
    0.93
     Er
    0.93
     Sk
    0.93
    Par
    0.92
     Ri
    0.92
     Sar
    0.91
    Act Density 2.675%

    No Known Activations