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

    Neuronpedia

    INDEX
    Explanations

    terms related to email addresses being already registered

    oai_token-act-pair · gpt-3.5-turbo

    terms related to processes of change or transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Frames
    -0.80
    ruciating
    -0.74
    pees
    -0.74
     elig
    -0.73
     Vive
    -0.72
     Croat
    -0.71
    ritis
    -0.71
    thood
    -0.70
    estinal
    -0.69
    doms
    -0.68
    POSITIVE LOGITS
     curve
    0.69
    swers
    0.63
     Shutterstock
    0.63
    alter
    0.62
    spin
    0.62
     reim
    0.62
     contag
    0.60
     brink
    0.60
     gradient
    0.60
     spelling
    0.58
    Act Density 0.000%

    No Known Activations