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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms indicating time or sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.68
    ſelf
    -0.63
    ()?;
    -0.63
    LLocation
    -0.63
    herself
    -0.62
     Geruch
    -0.61
    Bean
    -0.59
     Viter
    -0.58
     whofe
    -0.58
    bean
    -0.58
    POSITIVE LOGITS
    はじめに
    0.84
     it
    0.81
     we
    0.78
    ,
    0.69
     there
    0.68
     they
    0.66
    cumin
    0.66
    Luckily
    0.63
    Thankfully
    0.60
    gway
    0.60
    Act Density 0.507%

    No Known Activations