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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    addock
    -0.07
    .sap
    -0.06
    iyan
    -0.06
    leep
    -0.06
     mij
    -0.06
    wi
    -0.06
    hower
    -0.06
    lev
    -0.06
    egade
    -0.06
    _pkg
    -0.05
    POSITIVE LOGITS
     which
    0.09
    which
    0.08
    tach
    0.07
     коÑĤоÑĢÑĭм
    0.07
     every
    0.07
     each
    0.07
     Ñıке
    0.07
     itself
    0.07
    each
    0.07
     коÑĤоÑĢÑĭй
    0.07
    Act Density 0.110%

    No Known Activations