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

    Neuronpedia

    INDEX
    Explanations

    comparative language indicating similarity or correlation between populations and variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    similarity and comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.56
     purpoſe
    -0.54
    évaluateur
    -0.51
     pleaſure
    -0.51
     raiſ
    -0.49
     Pardavimas
    -0.49
     publicitaires
    -0.47
     subscript
    -0.47
     Szene
    -0.46
    ſelves
    -0.46
    POSITIVE LOGITS
     closest
    0.49
     rather
    0.42
     closer
    0.41
     Rather
    0.38
     nearest
    0.38
     eher
    0.37
     nearer
    0.36
    closest
    0.36
     Lik
    0.36
    Rather
    0.35
    Act Density 0.193%

    No Known Activations