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

    Neuronpedia

    INDEX
    Explanations

    verbs that indicate actions of trying, exploring, or planning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     marg
    -0.15
    ly
    -0.15
     æĿ
    -0.15
     Miner
    -0.15
    iment
    -0.14
    ness
    -0.14
    INLINE
    -0.14
    stro
    -0.13
    stad
    -0.13
    stick
    -0.13
    POSITIVE LOGITS
    ableView
    0.17
    able
    0.17
    ABLE
    0.17
    ibly
    0.16
    /report
    0.15
    ãģ¹ãģį
    0.15
    erable
    0.15
    á»ijt
    0.14
    /remove
    0.14
    ables
    0.14
    Act Density 0.115%

    No Known Activations