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

    Neuronpedia

    INDEX
    Explanations

    key figures and organizations associated with social or political movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Inactive
    -0.17
    ulan
    -0.17
    olo
    -0.14
    orthy
    -0.14
     IQ
    -0.13
    wyn
    -0.13
    uv
    -0.13
    oz
    -0.13
    ỳ
    -0.13
     ØŃÙĬÙĨ
    -0.13
    POSITIVE LOGITS
     instead
    0.48
     opposite
    0.38
     Instead
    0.38
    instead
    0.37
    Instead
    0.37
     naopak
    0.37
     contrary
    0.28
     Nope
    0.26
     contrario
    0.25
     ngược
    0.25
    Act Density 0.338%

    No Known Activations