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

    Neuronpedia

    INDEX
    Explanations

    code snippets or programming-related language, as it recognizes terms such as 'Ċ' which are common in code

    oai_token-act-pair · gpt-3.5-turbo

    instances of strong emotions or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ageing
    -0.91
     neighb
    -0.85
     synerg
    -0.81
     mature
    -0.80
     sacrific
    -0.80
     quir
    -0.80
     regener
    -0.80
     telesc
    -0.80
     invincible
    -0.79
     fermented
    -0.79
    POSITIVE LOGITS
    According
    1.88
    SPONSORED
    1.67
    Additionally
    1.63
    Advertisement
    1.59
    However
    1.59
    Furthermore
    1.56
    Earlier
    1.55
    Attorney
    1.53
    Following
    1.51
    Neither
    1.49
    Act Density 0.489%

    No Known Activations