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

    Neuronpedia

    INDEX
    Explanations

    phrases related to foundation and preparation for future events or studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     whoſe
    -0.70
     saites
    -0.67
     himſelf
    -0.66
     theſe
    -0.66
     myſelf
    -0.65
    <bos>
    -0.61
     övers
    -0.59
     ſhe
    -0.59
    PhysRevD
    -0.58
    руппа
    -0.58
    POSITIVE LOGITS
     future
    0.89
    future
    0.80
     eventual
    0.76
    Future
    0.68
     Future
    0.64
     subsequently
    0.63
     futuros
    0.62
     subsequent
    0.60
    later
    0.60
     foreshadow
    0.59
    Act Density 0.439%

    No Known Activations