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

    Neuronpedia

    INDEX
    Explanations

    words related to objects and items that are typically used by humans

    oai_token-act-pair · gpt-3.5-turbo

    words that end with specific suffixes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    earable
    -0.83
    RM
    -0.70
     Reps
    -0.69
    VR
    -0.69
    ukong
    -0.68
    utenberg
    -0.67
    ngth
    -0.67
     Expend
    -0.64
    itu
    -0.62
    ETH
    -0.61
    POSITIVE LOGITS
     beetle
    0.91
     beetles
    0.83
     sticks
    0.81
     balls
    0.79
     circle
    0.77
     paddle
    0.76
     gland
    0.76
     herd
    0.76
     lect
    0.76
     fences
    0.75
    Act Density 0.237%

    No Known Activations