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

    Neuronpedia

    INDEX
    Explanations

    text that expresses aspirations or improvements in one's situation or position

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

    Follows the word "the" or at the start of the sentence

    np_acts-logits-general · gemini-2.0-flash

    hard choice destiny

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nakalista
    -0.59
    ).(
    -0.59
    ）.
    -0.55
    .)
    -0.55
    ）
    -0.54
    円
    -0.51
    ).
    -0.51
    }}{{
    -0.51
    })(\
    -0.50
    hn
    -0.49
    POSITIVE LOGITS
     itſelf
    1.03
     myſelf
    0.90
     tartalomajánló
    0.87
     becauſe
    0.84
     themſelves
    0.83
     greateſt
    0.82
    ſelves
    0.78
     beſt
    0.76
     himſelf
    0.74
     fometimes
    0.74
    Act Density 0.439%

    No Known Activations