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

    Neuronpedia

    INDEX
    Explanations

    terms related to assessment or analysis of information

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Efq
    -1.16
     himſelf
    -1.05
     myſelf
    -1.02
     themſelves
    -1.01
     itſelf
    -0.97
     Jefus
    -0.93
     purpoſe
    -0.90
     Houſe
    -0.90
    ſelf
    -0.88
     iſt
    -0.87
    POSITIVE LOGITS
    בח
    0.57
     bah
    0.49
    RuntimeObject
    0.47
    ur
    0.45
    丘
    0.45
    Exp
    0.45
    libr
    0.44
    sequelize
    0.44
    simpleType
    0.44
    turbo
    0.44
    Act Density 0.427%

    No Known Activations