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

    Neuronpedia

    INDEX
    Explanations

    occurrences of prepositions and relational phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plings
    -0.15
    onta
    -0.15
    ilee
    -0.15
    uars
    -0.14
    kbd
    -0.14
    ông
    -0.14
    imers
    -0.14
     Tight
    -0.14
    TURE
    -0.14
     appearance
    -0.14
    POSITIVE LOGITS
    eda
    0.15
    ovel
    0.14
    poll
    0.14
    ousse
    0.14
    raction
    0.14
     cigars
    0.13
    ure
    0.13
    estre
    0.13
    APS
    0.13
     tact
    0.13
    Act Density 0.007%

    No Known Activations