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

    Neuronpedia

    INDEX
    Explanations

    concepts related to abstract connections and relationships among ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     become
    -0.15
    íĮĶ
    -0.14
     ampl
    -0.14
    æŃ©
    -0.14
    respond
    -0.14
    çīĻ
    -0.14
    bec
    -0.14
    ATAR
    -0.14
     becomes
    -0.14
    amar
    -0.14
    POSITIVE LOGITS
     turn
    0.21
     bring
    0.21
     transform
    0.21
    enable
    0.20
     enable
    0.20
     vault
    0.20
    bring
    0.19
    transform
    0.19
     Turn
    0.19
     convert
    0.19
    Act Density 0.073%

    No Known Activations