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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to performance capabilities and potential outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.61
    ogie
    -0.49
    UFF
    -0.48
    NB
    -0.48
    istered
    -0.44
    Ü
    -0.42
     metic
    -0.42
    DX
    -0.42
    microsoft
    -0.41
    Shell
    -0.41
    POSITIVE LOGITS
     someday
    1.04
     tomorrow
    0.92
     anytime
    0.79
     sooner
    0.77
     if
    0.62
    morrow
    0.62
     forever
    0.59
     sometime
    0.58
     future
    0.57
     next
    0.55
    Act Density 1.953%

    No Known Activations