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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote duration or persistence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     almost
    -0.17
    abal
    -0.16
    ote
    -0.16
    almost
    -0.15
    esome
    -0.15
     closest
    -0.15
     slightly
    -0.15
     Almost
    -0.15
    umb
    -0.15
    otal
    -0.15
    POSITIVE LOGITS
     much
    0.47
    much
    0.41
    Much
    0.36
     Much
    0.35
     many
    0.34
     very
    0.33
     molto
    0.30
    _many
    0.30
     muito
    0.29
     veel
    0.28
    Act Density 0.355%

    No Known Activations