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

    Neuronpedia

    INDEX
    Explanations

    words related to consequences of actions and potential risks

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express risk and potential increases related to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    books
    -0.76
    kef
    -0.74
    icians
    -0.73
    zag
    -0.72
    bl
    -0.71
    english
    -0.69
    mates
    -0.69
    ¾
    -0.67
    ĸļ
    -0.67
    cients
    -0.66
    POSITIVE LOGITS
     exponentially
    0.93
     awareness
    0.89
     intensity
    0.85
     likelihood
    0.82
     elevation
    0.82
     efficiency
    0.81
     availability
    0.80
     Capacity
    0.79
     capacity
    0.79
     visibility
    0.79
    Act Density 0.143%

    No Known Activations