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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating relationships or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     il
    -0.18
     èĻ
    -0.17
    (il
    -0.17
     da
    -0.16
    arel
    -0.16
     dela
    -0.16
     dal
    -0.15
    ,
    -0.15
     la
    -0.15
    boro
    -0.15
    POSITIVE LOGITS
    etro
    0.36
    agnost
    0.29
    urn
    0.29
     cui
    0.24
    resse
    0.23
    abet
    0.23
    abol
    0.22
     front
    0.21
     orig
    0.21
    rott
    0.21
    Act Density 0.008%

    No Known Activations