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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to being impacted by specific conditions or constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chables
    -0.50
    RegressionTest
    -0.49
    FunctionFlags
    -0.47
    isseaux
    -0.46
     πρά
    -0.46
    URLException
    -0.46
    nosaurus
    -0.46
     ſch
    -0.46
     voran
    -0.46
    lenz
    -0.45
    POSITIVE LOGITS
     subjected
    0.64
     undergo
    0.59
     undergoes
    0.54
     undergoing
    0.54
     sofrer
    0.53
     undergone
    0.51
     Subject
    0.48
    Subject
    0.47
    ỏa
    0.45
     subject
    0.44
    Act Density 0.439%

    No Known Activations