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

    Neuronpedia

    INDEX
    Explanations

    references to anniversaries and celebratory occasions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <
    -0.42
    float
    -0.39
    P
    -0.38
     $\
    -0.38
    </thead>
    -0.37
    Luke
    -0.36
    p
    -0.36
    0
    -0.35
    2
    -0.35
    ><
    -0.35
    POSITIVE LOGITS
     anniversary
    1.30
     anniversaries
    1.23
     Anniversary
    1.20
    ValueStyle
    1.18
    anniversary
    1.16
    versary
    1.07
     anniversaire
    1.01
     aniversario
    0.96
     anivers
    0.95
    Anni
    0.93
    Act Density 0.005%

    No Known Activations