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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "call" in various forms, indicating demands or requests for action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ubo
    -0.21
    atk
    -0.17
    /from
    -0.16
    ABOUT
    -0.15
    iners
    -0.15
    ADR
    -0.15
    aign
    -0.15
    rawl
    -0.14
    okit
    -0.14
    SizeMode
    -0.14
    POSITIVE LOGITS
     upon
    0.45
     attention
    0.37
     Upon
    0.34
     Attention
    0.31
    Upon
    0.31
    upon
    0.30
    attention
    0.25
    Attention
    0.25
     foul
    0.24
    ously
    0.22
    Act Density 0.024%

    No Known Activations