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

    Neuronpedia

    INDEX
    Explanations

    modal verbs denoting potential or future actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istle
    -0.16
    áli
    -0.16
    illis
    -0.14
    	Copyright
    -0.14
    Ñıж
    -0.14
    Compression
    -0.14
    ibilidade
    -0.14
    oret
    -0.14
     dục
    -0.14
    terminal
    -0.14
    POSITIVE LOGITS
    lauf
    0.16
     soon
    0.16
    boru
    0.16
     Trev
    0.15
    mina
    0.15
    ispers
    0.15
    iams
    0.15
    olt
    0.14
     later
    0.14
    ooth
    0.14
    Act Density 0.163%

    No Known Activations