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

    Neuronpedia

    INDEX
    Explanations

    prepositions and their variations in textual context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ARGER
    -0.15
     inne
    -0.14
    ijn
    -0.14
     Blond
    -0.14
    .Append
    -0.14
    dik
    -0.14
     Arb
    -0.14
     konce
    -0.13
    aspers
    -0.13
    abee
    -0.13
    POSITIVE LOGITS
    ighb
    0.19
    ertz
    0.15
    athers
    0.15
    ÑĢел
    0.14
     hood
    0.14
    posable
    0.14
    .Foundation
    0.14
    nul
    0.14
    ROY
    0.13
     Mug
    0.13
    Act Density 0.005%

    No Known Activations