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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social interactions and activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yu
    -0.14
    AMES
    -0.14
    onas
    -0.14
    igger
    -0.14
    hift
    -0.14
    ç½®
    -0.13
    باز
    -0.13
    adge
    -0.13
    autiful
    -0.13
    ube
    -0.13
    POSITIVE LOGITS
    strup
    0.18
    bjerg
    0.16
    æ´²
    0.15
    .um
    0.15
    reeNode
    0.15
    ighton
    0.14
    illac
    0.14
    shake
    0.14
    401
    0.14
    etooth
    0.14
    Act Density 0.184%

    No Known Activations