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

    Neuronpedia

    INDEX
    Explanations

    first-person singular verbs in negative form

    oai_token-act-pair · gpt-3.5-turbo

    expressions of surprise or disbelief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     neighb
    -0.61
    lishes
    -0.57
    ilaterally
    -0.55
     agric
    -0.53
    ufact
    -0.51
     municip
    -0.51
    ilst
    -0.50
    iann
    -0.50
    result
    -0.50
    osponsors
    -0.49
    POSITIVE LOGITS
     fuckin
    0.86
     fucking
    0.78
     gonna
    0.75
     funny
    0.68
     goddamn
    0.66
     uh
    0.65
     alright
    0.64
     kinda
    0.64
     fucked
    0.62
     stupid
    0.62
    Act Density 1.235%

    No Known Activations