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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking preventive measures or avoiding negative outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    avoid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pertory
    -0.51
    SpringRunner
    -0.51
    Cartney
    -0.51
    ReusableCell
    -0.50
     QtCore
    -0.50
     STM
    -0.48
    cke
    -0.48
     stringBuilder
    -0.48
    ⸻
    -0.47
     sentimenti
    -0.46
    POSITIVE LOGITS
     avoid
    1.59
    avoid
    1.57
    Avoid
    1.52
     Avoid
    1.51
     AVOID
    1.45
     avoiding
    1.41
     avoids
    1.41
     avoided
    1.37
    Avoiding
    1.32
     avoidance
    1.31
    Act Density 0.009%

    No Known Activations