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

    Neuronpedia

    INDEX
    Explanations

    nouns related to items or entities

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to entities and objects in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dhabi
    -0.71
    \\\\\\\\
    -0.69
    UTERS
    -0.64
     Disorder
    -0.63
    âĢ¢âĢ¢
    -0.62
     Ventures
    -0.60
    ALLY
    -0.60
     Zealand
    -0.59
    mington
    -0.58
    BALL
    -0.58
    POSITIVE LOGITS
     themselves
    1.19
    etter
    1.13
    mith
    1.12
    etting
    1.03
    cape
    1.01
    linger
    1.00
    hip
    0.99
    ensitive
    0.98
    heet
    0.97
    ettings
    0.95
    Act Density 0.365%

    No Known Activations