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

    Neuronpedia

    INDEX
    Explanations

    references to user engagement through comments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    efs
    -0.16
    lord
    -0.16
    itzer
    -0.15
    ervoir
    -0.15
    .tie
    -0.15
     Rhodes
    -0.15
    illance
    -0.14
    Opera
    -0.14
    ieu
    -0.14
    gg
    -0.14
    POSITIVE LOGITS
    γκο
    0.15
    648
    0.14
    itime
    0.14
    esub
    0.14
    509
    0.14
    ضاء
    0.14
    lashes
    0.14
    663
    0.14
    autos
    0.13
    737
    0.13
    Act Density 0.008%

    No Known Activations