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

    Neuronpedia

    INDEX
    Explanations

    questions and inquiries about experiences and motivations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.17
    lug
    -0.16
     crow
    -0.16
    enton
    -0.15
    zcze
    -0.15
     crown
    -0.14
    anager
    -0.14
    enth
    -0.14
    å·
    -0.14
    .gwt
    -0.14
    POSITIVE LOGITS
    dam
    0.17
    reo
    0.15
    æ¤į
    0.15
    éī
    0.14
    iates
    0.14
     κÏĮ
    0.14
    ivalence
    0.14
    ê¶ģ
    0.14
     relat
    0.14
    ives
    0.13
    Act Density 0.220%

    No Known Activations