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

    Neuronpedia

    INDEX
    Explanations

    Proper names

    oai_token-act-pair · gpt-3.5-turbo

    proper names, particularly those related to individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģŁ
    -0.75
    ODUCT
    -0.75
     subsistence
    -0.74
     Barbarian
    -0.72
    ãĥīãĥ©ãĤ´ãĥ³
    -0.72
    ãĥīãĥ©
    -0.72
    ffic
    -0.70
    OPER
    -0.69
    å¸
    -0.65
    Translation
    -0.64
    POSITIVE LOGITS
     Benn
    1.25
    elong
    1.09
    etooth
    0.92
    igans
    0.88
    nect
    0.85
    ella
    0.82
    jamin
    0.81
    stadt
    0.81
    acles
    0.81
    essa
    0.80
    Act Density 0.005%

    No Known Activations