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

    Neuronpedia

    INDEX
    Explanations

    phrases related to events and activities leading up to a particular occurrence

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "running up" or increasing amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rosenstein
    -0.61
     Logged
    -0.57
     backbone
    -0.57
    ij士
    -0.57
     chang
    -0.57
     srfAttach
    -0.56
    CAN
    -0.55
    ��
    -0.55
    ...]
    -0.55
    VILLE
    -0.55
    POSITIVE LOGITS
    profits
    0.89
    dating
    0.88
    heid
    0.81
    stairs
    0.81
    cycl
    0.77
    dates
    0.77
    selling
    0.75
    market
    0.74
    wards
    0.74
    pread
    0.73
    Act Density 0.026%

    No Known Activations