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

    Neuronpedia

    INDEX
    Explanations

    events or actions related to criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of hacking or breaches of security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.53
    eways
    -0.52
    Bio
    -0.52
    cour
    -0.52
    ofi
    -0.51
     bask
    -0.49
     :=
    -0.49
    algia
    -0.49
    ependence
    -0.49
     pops
    -0.49
    POSITIVE LOGITS
     Bulgar
    0.60
     illegally
    0.60
     "âĢ¦
    0.59
     inappropriately
    0.59
     unlawfully
    0.59
     wrong
    0.59
     improper
    0.58
     prostitutes
    0.58
     "'
    0.57
     Paddock
    0.55
    Act Density 1.372%

    No Known Activations