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

    Neuronpedia

    INDEX
    Explanations

    words related to specific areas within a field or context

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    aldi
    -0.84
    thora
    -0.80
    sonian
    -0.80
    anooga
    -0.79
    issance
    -0.77
    tons
    -0.72
     Bones
    -0.70
    HCR
    -0.70
    verified
    -0.70
    Hunt
    -0.70
    POSITIVE LOGITS
     zones
    1.07
     zone
    1.03
     dwell
    0.91
     boundary
    0.81
     boundaries
    0.79
     deline
    0.76
     Zone
    0.76
     area
    0.74
     Areas
    0.73
     areas
    0.72
    Act Density 0.077%

    No Known Activations