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

    Neuronpedia

    INDEX
    Explanations

    phrases introducing statements or explanations

    oai_token-act-pair · gpt-3.5-turbo

    clauses or phrases that assert information or claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogether
    -0.71
    onder
    -0.58
    ãĤ©
    -0.57
    rily
    -0.57
    userc
    -0.55
    ãĥ³ãĤ¸
    -0.54
    sequently
    -0.53
     Vaugh
    -0.53
    estones
    -0.53
    ays
    -0.53
    POSITIVE LOGITS
     [+
    0.67
     Allaah
    0.65
     graphene
    0.56
     Xiaomi
    0.56
     Quote
    0.56
     Capitalism
    0.56
     ISPs
    0.55
     systemd
    0.54
     SpaceX
    0.54
     Canaver
    0.54
    Act Density 0.486%

    No Known Activations