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

    Neuronpedia

    INDEX
    Explanations

    terms related to medical conditions or treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ylon
    -0.15
     religious
    -0.15
    yle
    -0.14
    evil
    -0.14
    aire
    -0.14
    .Mutable
    -0.14
    kar
    -0.14
    ure
    -0.14
    ilton
    -0.13
    еÑģÑĤв
    -0.13
    POSITIVE LOGITS
    linger
    0.18
    imals
    0.16
    conto
    0.16
    -enable
    0.15
    reon
    0.15
    ijke
    0.14
     Mour
    0.14
     Decay
    0.14
    elts
    0.14
    ãģ£ãģı
    0.14
    Act Density 0.017%

    No Known Activations