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

    Neuronpedia

    INDEX
    Explanations

    phrases related to various specific topics like databases, thread names, ingredients, IP addresses, veterans, etc

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to technical or specialized concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ZI
    -0.66
    Enlarge
    -0.53
    Joined
    -0.50
    EMA
    -0.49
    Fla
    -0.49
    Miami
    -0.48
    Native
    -0.48
    Primary
    -0.48
    Commerce
    -0.47
    la
    -0.46
    POSITIVE LOGITS
     cannot
    0.81
     may
    0.76
     consists
    0.76
     underwent
    0.75
     consisted
    0.74
     contains
    0.73
     behaves
    0.71
     survived
    0.71
     fared
    0.70
     lasted
    0.70
    Act Density 0.695%

    No Known Activations