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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "in" and phrases related to conditions and statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oje
    -0.16
     herself
    -0.15
    emouth
    -0.15
    Borders
    -0.14
    asy
    -0.14
    ------+------+
    -0.14
    彼女
    -0.13
    και
    -0.13
     zdrav
    -0.13
     lum
    -0.13
    POSITIVE LOGITS
    ourd
    0.15
    ius
    0.15
    åĽ£
    0.15
     Pax
    0.15
    SystemService
    0.14
    itant
    0.13
     join
    0.13
    iot
    0.13
    QUIT
    0.13
    omed
    0.13
    Act Density 0.060%

    No Known Activations