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

    Neuronpedia

    INDEX
    Explanations

    various prepositions and their contextual usage in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antan
    -0.18
    sgiving
    -0.15
    flo
    -0.14
    sher
    -0.14
    BSD
    -0.14
     outsider
    -0.14
    iams
    -0.14
     Outputs
    -0.14
    itz
    -0.14
    彩
    -0.14
    POSITIVE LOGITS
     nowhere
    0.36
     bounds
    0.31
     reach
    0.28
     sight
    0.27
     commission
    0.23
     Bounds
    0.23
     pocket
    0.23
     harms
    0.23
     thin
    0.23
    _bounds
    0.22
    Act Density 0.048%

    No Known Activations