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

    Neuronpedia

    INDEX
    Explanations

    phrases related to short-term situations or goals

    oai_token-act-pair · gpt-3.5-turbo

    references to "short term" situations or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ILLE
    -0.93
    GAN
    -0.73
    Magikarp
    -0.72
    IRO
    -0.70
    itational
    -0.70
    ONSORED
    -0.69
    IAN
    -0.68
    iance
    -0.68
    ashtra
    -0.67
    antine
    -0.67
    POSITIVE LOGITS
    sighted
    1.13
    ening
    1.00
    lived
    0.98
    sword
    0.93
    short
    0.92
    falls
    0.90
    ener
    0.89
    ened
    0.89
    changed
    0.87
     bursts
    0.86
    Act Density 0.022%

    No Known Activations