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

    Neuronpedia

    INDEX
    Explanations

    connections and relationships within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atron
    -0.16
    ikan
    -0.15
    swer
    -0.15
    stri
    -0.14
    cheon
    -0.14
    endar
    -0.14
    rica
    -0.14
    odesk
    -0.13
    olia
    -0.13
     Others
    -0.13
    POSITIVE LOGITS
     types
    0.20
     accred
    0.16
     combinations
    0.16
     withd
    0.15
     depths
    0.15
    bos
    0.15
    imes
    0.15
     Types
    0.15
     seasons
    0.15
     sizes
    0.15
    Act Density 0.131%

    No Known Activations