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

    Neuronpedia

    INDEX
    Explanations

    terms related to stability and continuity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÌĨ
    -0.17
    marvin
    -0.15
    prot
    -0.15
    -back
    -0.14
    rus
    -0.14
     sitting
    -0.13
    =no
    -0.13
     ·
    -0.13
    lay
    -0.13
     nowhere
    -0.13
    POSITIVE LOGITS
     throughout
    0.23
     until
    0.21
     longer
    0.21
    Until
    0.20
    à¹Ħว
    0.20
    until
    0.20
     Longer
    0.19
     Until
    0.19
    _until
    0.19
     longest
    0.18
    Act Density 0.187%

    No Known Activations