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

    Neuronpedia

    INDEX
    Explanations

    references to academic journals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ewn
    -0.16
    zk
    -0.16
    annes
    -0.15
     nieu
    -0.15
    enstein
    -0.15
    anel
    -0.15
    asser
    -0.14
    uti
    -0.14
    -www
    -0.14
    abox
    -0.14
    POSITIVE LOGITS
    istic
    0.30
    isted
    0.23
    ists
    0.23
    ize
    0.22
    izes
    0.21
    istically
    0.21
    istics
    0.20
    izing
    0.20
    ized
    0.20
    ization
    0.19
    Act Density 0.016%

    No Known Activations