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

    Neuronpedia

    INDEX
    Explanations

    words related to the prefix 'prot-'

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "rot" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.76
    ept
    -0.67
     cumbers
    -0.65
    pler
    -0.65
    viation
    -0.63
    College
    -0.62
     labour
    -0.62
    resso
    -0.61
    BLE
    -0.60
    BILITIES
    -0.60
    POSITIVE LOGITS
    ting
    0.93
    chet
    0.86
    ation
    0.83
    iful
    0.83
    rot
    0.82
    urtle
    0.81
    ter
    0.80
    ected
    0.80
    tery
    0.79
    omy
    0.78
    Act Density 0.016%

    No Known Activations