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

    Neuronpedia

    INDEX
    Explanations

    concepts related to humanity and human existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illow
    -0.16
     Gund
    -0.15
     Joy
    -0.15
    aceae
    -0.14
    olley
    -0.14
    ika
    -0.14
    obao
    -0.14
    Joy
    -0.14
    assy
    -0.14
    ours
    -0.14
    POSITIVE LOGITS
    θÏħ
    0.19
    ROSS
    0.15
     beings
    0.15
    oucher
    0.15
    ifen
    0.14
     elect
    0.14
    .CONFIG
    0.13
     yem
    0.13
    VF
    0.13
    øre
    0.13
    Act Density 0.107%

    No Known Activations