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

    Neuronpedia

    INDEX
    Explanations

    exclamatory statements and commands

    oai_token-act-pair · gpt-3.5-turbo

    phrases or expressions indicating strong emotional reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reclaimed
    -0.74
     metic
    -0.74
     conj
    -0.71
     preserved
    -0.70
     featured
    -0.68
     recomb
    -0.68
     tangled
    -0.67
     fused
    -0.67
     targeted
    -0.67
     entangled
    -0.67
    POSITIVE LOGITS
    Hey
    1.09
    Everybody
    1.04
    everyone
    1.04
    why
    1.04
    please
    1.03
    Look
    1.01
    Okay
    1.00
    nob
    0.98
    there
    0.96
    everything
    0.96
    Act Density 0.047%

    No Known Activations