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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating perceptions or assumptions about situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sever
    -0.16
    à¹Īาย
    -0.15
    æ¯Ķ
    -0.14
    çĥ
    -0.14
     bv
    -0.14
    dition
    -0.14
     footing
    -0.14
     Ñĥда
    -0.14
    auty
    -0.13
    ãģij
    -0.13
    POSITIVE LOGITS
     Beste
    0.15
    \grid
    0.15
    /Runtime
    0.15
    allah
    0.15
     sinister
    0.15
    ä¸ĸç´Ģ
    0.14
    .btnClose
    0.14
    ascript
    0.14
    PIP
    0.14
    stoff
    0.14
    Act Density 0.270%

    No Known Activations