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

    Neuronpedia

    INDEX
    Explanations

    words related to technical computing concepts and processes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    mouth
    -0.77
    roller
    -0.74
    shr
    -0.70
    rooms
    -0.69
    mir
    -0.69
    phis
    -0.68
    talk
    -0.64
    heartedly
    -0.64
    eye
    -0.64
    room
    -0.62
    POSITIVE LOGITS
    minist
    0.88
    iable
    0.85
     from
    0.79
     deriv
    0.74
    ministic
    0.73
     derive
    0.73
     thereof
    0.72
     derived
    0.72
     neurot
    0.72
    acet
    0.71
    Act Density 0.044%

    No Known Activations