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

    Neuronpedia

    INDEX
    Explanations

    strong emotional reactions or intense captivation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to captivity and capture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bye
    -0.70
     donor
    -0.68
     holiest
    -0.68
     prone
    -0.68
     joint
    -0.66
     Integrity
    -0.65
     onwards
    -0.64
     trust
    -0.63
     paternity
    -0.63
     Patriot
    -0.63
    POSITIVE LOGITS
    ivating
    1.19
    ained
    1.15
    aining
    1.10
    Capt
    1.07
    ains
    1.06
    ivated
    1.04
    iors
    0.98
    urable
    0.94
    anted
    0.94
    oded
    0.93
    Act Density 0.009%

    No Known Activations