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

    Neuronpedia

    INDEX
    Explanations

    terms associated with advantages and efficacy in methods or processes

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

    Follows words indicating ease or simplicity

    np_acts-logits-general · gemini-2.0-flash

    easy and convenient

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unlucky
    -0.58
    残念ながら
    -0.55
    ureusement
    -0.54
     серпня
    -0.52
     imageNamed
    -0.51
     infeliz
    -0.49
     okuyayım
    -0.48
     insufic
    -0.47
     anteriore
    -0.47
     vorder
    -0.46
    POSITIVE LOGITS
     easy
    1.55
    easy
    1.30
     easily
    1.22
     Easy
    1.22
    Easy
    1.18
     ease
    1.18
     easier
    1.15
     cost
    1.11
     łat
    1.10
     fácil
    1.10
    Act Density 0.625%

    No Known Activations