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

    Neuronpedia

    INDEX
    Explanations

    phrases related to offering compliments or expressing appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.65
    '
    -0.61
    \[
    -0.55
     C
    -0.54
    <eos>
    -0.54
     D
    -0.51
     on
    -0.48
    ’
    -0.47
     B
    -0.47
    ss
    -0.46
    POSITIVE LOGITS
     excellent
    1.13
     terrific
    1.09
     tremendous
    1.04
     very
    1.02
     fantastic
    1.02
    WithIOException
    1.00
     wonderful
    0.99
    SequentialGroup
    0.98
    excellent
    0.98
     amazing
    0.97
    Act Density 0.601%

    No Known Activations