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

    Neuronpedia

    INDEX
    Explanations

    things related to assignments or tasks that need to be completed

    oai_token-act-pair · gpt-3.5-turbo

    references to academic or task-related assignments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ïī
    -0.74
    mph
    -0.72
     supra
    -0.71
    FORE
    -0.71
    vae
    -0.70
    ASE
    -0.66
    enthal
    -0.66
    bite
    -0.65
    α
    -0.64
    gling
    -0.64
    POSITIVE LOGITS
     assignment
    1.22
     Assignment
    1.03
     assignments
    1.02
     homework
    0.78
    ointed
    0.74
     attendant
    0.74
    idon
    0.73
    æ©Ł
    0.72
    ignment
    0.71
     lesson
    0.70
    Act Density 0.010%

    No Known Activations