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

    Neuronpedia

    INDEX
    Explanations

    phrases related to problem-solving and mechanisms in systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Alternative
    -0.51
    Alternative
    -0.47
     alternative
    -0.45
    No
    -0.44
    Non
    -0.43
    non
    -0.41
     van
    -0.41
    no
    -0.40
    R
    -0.40
     Go
    -0.39
    POSITIVE LOGITS
    @[+][
    0.89
    ArrowToggle
    0.81
    gameserver
    0.79
    Numerology
    0.77
    httphttps
    0.75
    weds
    0.74
     CreateTagHelper
    0.73
    TagMode
    0.73
    ✨:
    0.73
    Искәрмәләр
    0.72
    Act Density 0.776%

    No Known Activations