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

    Neuronpedia

    INDEX
    Explanations

    references to the physical structure of objects or containers, particularly focusing on dimensions and internal features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roma
    -0.15
    stra
    -0.15
    ames
    -0.15
    idden
    -0.15
    ome
    -0.14
    aren
    -0.14
    identity
    -0.14
    uel
    -0.14
    emen
    -0.14
    ison
    -0.13
    POSITIVE LOGITS
    ALLED
    0.16
     Hurt
    0.15
    ACHE
    0.15
    webs
    0.14
    ERM
    0.14
    ocode
    0.14
    decay
    0.14
    teri
    0.14
    /out
    0.14
    IRCLE
    0.14
    Act Density 0.043%

    No Known Activations