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

    Neuronpedia

    INDEX
    Explanations

    affirmative statements and expressions of gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.18
    Sexy
    -0.16
    (Source
    -0.16
     COVID
    -0.16
     Covid
    -0.15
    ovid
    -0.14
    .related
    -0.14
    https
    -0.14
    -Compatible
    -0.14
    .*/↵
    -0.14
    POSITIVE LOGITS
    Copyright
    0.32
     Copyright
    0.29
    1
    0.22
    ©
    0.22
    �
    0.20
    is
    0.19
    are
    0.19
    hi
    0.19
    ă
    0.19
     copyright
    0.19
    Act Density 1.356%

    No Known Activations