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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating future actions or possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ç¸
    -0.15
    quirrel
    -0.15
     JADX
    -0.14
    posables
    -0.14
     flexGrow
    -0.14
    guard
    -0.14
     ë¶Ļ
    -0.14
    ough
    -0.14
    akit
    -0.13
     pylint
    -0.13
    POSITIVE LOGITS
     Dün
    0.16
    ÑĩаÑĤ
    0.14
    ongo
    0.14
     be
    0.14
    INGS
    0.13
    aler
    0.13
    Operation
    0.13
     amac
    0.13
    AW
    0.13
     dap
    0.13
    Act Density 0.191%

    No Known Activations