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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" and its variations in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hod
    -0.16
    ky
    -0.15
    ering
    -0.15
    orman
    -0.15
    lder
    -0.14
    ÑıÑģÑĮ
    -0.14
    ymoon
    -0.14
    wards
    -0.14
    ovable
    -0.14
    atcher
    -0.13
    POSITIVE LOGITS
     bear
    0.27
    bear
    0.25
    Bear
    0.20
     boil
    0.19
     attention
    0.18
     table
    0.17
     Bear
    0.17
     fruition
    0.17
    collapsed
    0.17
    czy
    0.16
    Act Density 0.036%

    No Known Activations