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

    Neuronpedia

    INDEX
    Explanations

    phrases or questions about reading and personal reflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     DEAL
    -0.17
    èªī
    -0.14
    SizePolicy
    -0.14
    HIR
    -0.14
    .gf
    -0.14
    .sul
    -0.14
    laÄį
    -0.14
     Datensch
    -0.14
    .CreateDirectory
    -0.14
     Hlav
    -0.13
    POSITIVE LOGITS
    Ùħت
    0.15
    onymous
    0.14
    wner
    0.13
     superv
    0.13
     Foot
    0.13
     ___
    0.13
    âĦ¢
    0.12
     Superv
    0.12
     viz
    0.12
    cas
    0.12
    Act Density 0.177%

    No Known Activations