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

    Neuronpedia

    INDEX
    Explanations

    concepts related to human development and the evolution of society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Fail
    -0.15
     Hood
    -0.15
     omn
    -0.14
     Canc
    -0.14
     hungry
    -0.14
    缩
    -0.13
     cancell
    -0.13
    ewe
    -0.13
    arc
    -0.13
    esan
    -0.13
    POSITIVE LOGITS
    comings
    0.22
     rh
    0.21
     Nom
    0.18
    rh
    0.18
     molec
    0.18
     Fold
    0.17
    clinic
    0.17
     plateau
    0.17
     nom
    0.17
    Nom
    0.17
    Act Density 0.005%

    No Known Activations