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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical instructions or procedures

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to technical operations and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     strikingly
    -0.76
     adherents
    -0.68
     revered
    -0.67
     Sheikh
    -0.66
     revolutionary
    -0.65
     embodies
    -0.63
     Cosponsors
    -0.63
     epit
    -0.63
     unsur
    -0.63
     understandably
    -0.63
    POSITIVE LOGITS
    )).
    0.98
    ))))
    0.80
     haha
    0.77
    ļéĨĴ
    0.74
     lug
    0.74
    ventory
    0.73
     anyways
    0.73
     exha
    0.72
     lol
    0.71
     reload
    0.70
    Act Density 1.174%

    No Known Activations