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

    Neuronpedia

    INDEX
    Explanations

    verbs related to control or influence, particularly when it involves steering or warding off something

    oai_token-act-pair · gpt-3.5-turbo

    words related to guidance or direction, particularly in the context of avoiding or moving away from something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.72
    jug
    -0.59
    eds
    -0.59
     digits
    -0.57
    ities
    -0.57
     suffix
    -0.56
     bunk
    -0.55
     produ
    -0.54
    ylon
    -0.54
     diction
    -0.54
    POSITIVE LOGITS
     away
    1.15
     Away
    0.91
     aside
    0.83
    oided
    0.82
     clear
    0.79
     awa
    0.77
     toward
    0.77
     Towards
    0.76
     off
    0.75
    osite
    0.73
    Act Density 0.176%

    No Known Activations