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

    Neuronpedia

    INDEX
    Explanations

    phrases related to evaluations of quality or effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     때문
    -0.56
     autant
    -0.51
    secret
    -0.49
    偏偏
    -0.46
    あえて
    -0.46
     nhất
    -0.46
     secreto
    -0.46
    gabe
    -0.45
    ありますか
    -0.44
     šte
    -0.44
    POSITIVE LOGITS
     nice
    1.88
     lovely
    1.88
     wonderful
    1.84
     beautiful
    1.69
     interesting
    1.69
     excellent
    1.63
     fantastic
    1.63
    wonderful
    1.60
    lovely
    1.60
     terrific
    1.53
    Act Density 0.398%

    No Known Activations