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

    Neuronpedia

    INDEX
    Explanations

    mathematical notations and definitions related to parameters in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jackson
    -0.15
    ouch
    -0.15
    rai
    -0.15
    zd
    -0.14
     Mechan
    -0.14
     McK
    -0.14
    hydrate
    -0.14
     Mech
    -0.14
     +
    -0.14
    Reviewed
    -0.13
    POSITIVE LOGITS
     defined
    0.25
     Defined
    0.25
    defined
    0.22
     :=
    0.20
     definition
    0.20
    íĨłíĨł
    0.18
     :=↵
    0.17
    å®ļä¹ī
    0.17
     meaning
    0.17
    senal
    0.17
    Act Density 0.207%

    No Known Activations