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

    Neuronpedia

    INDEX
    Explanations

    phrases related to scientific mechanisms or processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mechanisms and actions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iaries
    -0.81
     Oval
    -0.74
    fle
    -0.70
    raid
    -0.69
    hiro
    -0.67
    sch
    -0.67
    enza
    -0.66
    apest
    -0.64
    gard
    -0.63
    igi
    -0.63
    POSITIVE LOGITS
     whereby
    1.25
     mechanism
    1.01
     Mechan
    0.96
     mechanisms
    0.92
    utics
    0.86
     linking
    0.85
     governing
    0.84
    isms
    0.82
     underlying
    0.81
     controlling
    0.80
    Act Density 0.060%

    No Known Activations