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

    Neuronpedia

    INDEX
    Explanations

    programming-related file types and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lander
    -0.17
    лой
    -0.15
    odiac
    -0.15
    ote
    -0.15
     illusion
    -0.14
     ow
    -0.14
     Die
    -0.14
     suit
    -0.14
    on
    -0.13
    asan
    -0.13
    POSITIVE LOGITS
    bury
    0.15
    opis
    0.15
    dess
    0.14
    erland
    0.14
    ῶ
    0.14
    chalk
    0.14
    еÑĢв
    0.14
    erv
    0.14
    npos
    0.14
    _marshall
    0.14
    Act Density 0.001%

    No Known Activations