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

    Neuronpedia

    INDEX
    Explanations

    expressions of preference or favorites

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bart
    -0.15
     toda
    -0.15
    ilet
    -0.15
    ocup
    -0.15
    ega
    -0.14
    loo
    -0.14
    UMB
    -0.14
    alk
    -0.14
    expo
    -0.14
    InvalidArgumentException
    -0.14
    POSITIVE LOGITS
    -ever
    0.21
     childhood
    0.21
     moments
    0.18
     Childhood
    0.18
    erals
    0.17
    kind
    0.16
     amongst
    0.16
     among
    0.16
     memories
    0.15
    /pass
    0.15
    Act Density 0.017%

    No Known Activations