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

    Neuronpedia

    INDEX
    Explanations

    words related to official titles, terms, or organizational roles

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "coordination" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etsk
    -0.90
    prus
    -0.71
     midterm
    -0.70
    kered
    -0.70
    zza
    -0.70
    kins
    -0.66
    CVE
    -0.65
    ======
    -0.65
    terson
    -0.65
    grades
    -0.63
    POSITIVE LOGITS
    inator
    1.12
    inates
    1.06
    inated
    1.02
    nance
    1.01
    inators
    0.93
    ination
    0.93
    inately
    0.92
    inarily
    0.91
    inances
    0.87
    inating
    0.86
    Act Density 0.026%

    No Known Activations