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

    Neuronpedia

    INDEX
    Explanations

    instances of doubt or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apiro
    -0.16
    -Ñħ
    -0.15
    ahat
    -0.15
     Conj
    -0.14
    loh
    -0.14
     Grimm
    -0.14
    umbn
    -0.14
     suburban
    -0.13
    _GLOBAL
    -0.13
     proc
    -0.13
    POSITIVE LOGITS
    ansible
    0.22
     ansible
    0.20
     Hein
    0.17
     kz
    0.16
    aran
    0.15
     Benchmark
    0.15
    µľ
    0.15
     Cord
    0.15
     Hari
    0.14
     Spacer
    0.14
    Act Density 0.090%

    No Known Activations