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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "in."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    duct
    -0.28
    ducted
    -0.23
    ductive
    -0.19
    ÑĢÑıдÑĥ
    -0.18
    curring
    -0.16
    enville
    -0.16
    urally
    -0.16
    leans
    -0.16
    plevel
    -0.16
    /from
    -0.15
    POSITIVE LOGITS
    vol
    0.31
    ability
    0.30
    formed
    0.29
    ward
    0.28
    ade
    0.27
    ertia
    0.27
    hib
    0.26
    fl
    0.26
    complete
    0.25
    format
    0.25
    Act Density 0.160%

    No Known Activations