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

    Neuronpedia

    INDEX
    Explanations

    names and historical terms related to various locations and figures

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names associated with people and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rollout
    -0.90
     Comcast
    -0.85
     analytics
    -0.85
     actionGroup
    -0.83
     cybersecurity
    -0.82
     targeting
    -0.80
     transitioning
    -0.80
     broadcasting
    -0.80
     targeted
    -0.79
     partnering
    -0.78
    POSITIVE LOGITS
    û
    1.08
    onian
    1.07
    ü
    1.06
    æ
    1.03
    á¸
    1.01
    inus
    0.98
    Åį
    0.97
    anus
    0.96
    Å
    0.94
    idae
    0.94
    Act Density 0.568%

    No Known Activations