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

    Neuronpedia

    INDEX
    Explanations

    mentions of something being "constant" or permanently existing

    oai_token-act-pair · gpt-3.5-turbo

    the concept of ongoing or persistent situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RD
    -0.86
    hak
    -0.82
    ramid
    -0.82
    IDA
    -0.80
    ologies
    -0.78
     Halls
    -0.75
     Plants
    -0.75
    geist
    -0.75
    stra
    -0.72
    ells
    -0.72
    POSITIVE LOGITS
     constant
    0.98
     vigilance
    0.96
     tension
    0.88
    ãĥ¼ãĥĨãĤ£
    0.87
     Constant
    0.80
     gunfire
    0.80
    motion
    0.80
     reminder
    0.79
     attrition
    0.79
     intervals
    0.79
    Act Density 0.012%

    No Known Activations