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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize the frequency or abundance of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     chained
    -0.15
    aits
    -0.15
     Hills
    -0.15
    ansen
    -0.14
    Retention
    -0.14
    elop
    -0.14
     ult
    -0.13
     дал
    -0.13
    èĨ
    -0.13
     bra
    -0.13
    POSITIVE LOGITS
    OfClass
    0.16
    <context
    0.15
    ihn
    0.15
    ola
    0.15
    weg
    0.15
    NEL
    0.14
    _inline
    0.14
    ÏĥÏĥ
    0.14
    cki
    0.14
    pile
    0.13
    Act Density 0.058%

    No Known Activations