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

    Neuronpedia

    INDEX
    Explanations

    references to internal states or status indicators in a code context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ]--;
    -0.93
    ]='\
    -0.83
    ')")
    -0.78
    ]")
    -0.77
    MockMvc
    -0.76
    ])/
    -0.74
    }')
    -0.74
    ]')
    -0.72
    wixt
    -0.72
    ']")
    -0.72
    POSITIVE LOGITS
    state
    1.42
     state
    1.31
    STATE
    1.30
    states
    1.27
     states
    1.26
    State
    1.24
     STATE
    1.15
    States
    1.08
    状态
    1.06
     State
    1.05
    Act Density 0.078%

    No Known Activations