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

    Neuronpedia

    INDEX
    Explanations

    references to confusion or misunderstanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asto
    -0.15
    Matchers
    -0.15
    -vs
    -0.15
    ä¹ħ
    -0.15
    andas
    -0.15
    lify
    -0.15
    lein
    -0.15
    tempts
    -0.14
    unan
    -0.14
    preter
    -0.14
    POSITIVE LOGITS
    /conf
    0.19
     waters
    0.17
    ÑıÑĩ
    0.16
     Waters
    0.15
    ephir
    0.15
     Bros
    0.14
     confuse
    0.14
     Cul
    0.14
    ĶĶ
    0.14
    .apple
    0.14
    Act Density 0.032%

    No Known Activations