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

    Neuronpedia

    INDEX
    Explanations

    statements regarding mathematical equivalences and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ͅ
    -0.54
    ∉
    -0.51
    modb
    -0.51
     helst
    -0.49
     frais
    -0.49
     nicely
    -0.48
    enapa
    -0.47
    ünstig
    -0.46
    følgelig
    -0.45
     voks
    -0.45
    POSITIVE LOGITS
     equivalent
    1.15
    Equivalent
    1.10
     Equivalent
    1.09
    equivalent
    1.08
     equival
    1.05
     equivalente
    1.04
     equivalence
    1.03
     équi
    1.03
     equivalents
    0.99
     equivale
    0.95
    Act Density 0.459%

    No Known Activations