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

    Neuronpedia

    INDEX
    Explanations

    the word "In" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    duct
    -0.31
    ducted
    -0.25
    ductive
    -0.22
    temps
    -0.18
    ductor
    -0.17
    aron
    -0.17
    Ñī
    -0.16
    dg
    -0.15
    ients
    -0.15
    dar
    -0.15
    POSITIVE LOGITS
    ability
    0.33
    land
    0.28
    ward
    0.27
    clusive
    0.27
    hib
    0.26
    vol
    0.26
    fl
    0.24
    tra
    0.24
    formed
    0.24
    ertia
    0.23
    Act Density 0.096%

    No Known Activations