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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the phrase "tens of" followed by a number or quantity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    faker
    -0.17
    tes
    -0.16
    ÚĨÙĩ
    -0.16
    tesy
    -0.16
    ocz
    -0.16
    پس
    -0.16
    otts
    -0.15
    ocker
    -0.15
    cue
    -0.15
    oggler
    -0.15
    POSITIVE LOGITS
    ile
    0.26
    eness
    0.20
    ely
    0.19
    ilet
    0.18
     upon
    0.18
    ons
    0.17
    ILE
    0.17
    ed
    0.17
    ión
    0.17
    -of
    0.16
    Act Density 0.009%

    No Known Activations