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

    Neuronpedia

    INDEX
    Explanations

    words related to names and identities, particularly those with a focus on suffix patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uce
    -0.15
     Angie
    -0.14
    lya
    -0.14
    Äĩe
    -0.14
    avicon
    -0.14
    ifo
    -0.13
    isset
    -0.13
    íݸ
    -0.13
    umi
    -0.13
     Angelo
    -0.13
    POSITIVE LOGITS
    meer
    0.19
    ANCELED
    0.15
    änner
    0.15
    phia
    0.14
    otec
    0.14
    arResult
    0.14
    lastic
    0.13
    arra
    0.13
     noqa
    0.13
     Pruitt
    0.13
    Act Density 0.117%

    No Known Activations