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

    Neuronpedia

    INDEX
    Explanations

    descriptions of softness in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ArgumentParser
    -0.75
     Diz
    -0.71
    ActionCreators
    -0.66
    glEnd
    -0.64
    ("/:
    -0.63
    Clue
    -0.63
     beaker
    -0.63
    ganu
    -0.62
    FormTagHelper
    -0.62
    ủi
    -0.62
    POSITIVE LOGITS
     soft
    3.63
     Soft
    3.48
    soft
    3.36
    Soft
    3.33
     SOFT
    3.24
    SOFT
    2.90
     softness
    2.65
     softer
    2.58
     softly
    2.07
    软
    2.05
    Act Density 0.044%

    No Known Activations