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

    Neuronpedia

    INDEX
    Explanations

    names of contributors and participants in research studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Signalez
    -0.57
     nakalista
    -0.54
     mijne
    -0.53
     Independencia
    -0.52
    protoimpl
    -0.50
    parsedMessage
    -0.49
     vielmehr
    -0.49
    setupUi
    -0.49
    avoit
    -0.48
     queſta
    -0.46
    POSITIVE LOGITS
     spiral
    0.60
     psychological
    0.56
     Gy
    0.56
     Spiral
    0.55
     gy
    0.52
    endphp
    0.52
    ano
    0.51
     spirals
    0.51
     pathological
    0.50
     Psychological
    0.50
    Act Density 1.390%

    No Known Activations