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

    Neuronpedia

    INDEX
    Explanations

    phrases related to tightness or constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hoot
    -0.15
    iverz
    -0.15
    hra
    -0.15
    atee
    -0.15
    Ø©
    -0.14
    ì¹ĺ
    -0.14
    usch
    -0.14
    767
    -0.14
    875
    -0.14
     muj
    -0.14
    POSITIVE LOGITS
    ening
    0.31
    est
    0.28
    ness
    0.27
    ened
    0.27
    ens
    0.25
    eners
    0.23
    ener
    0.23
     knit
    0.22
    /loose
    0.22
    fit
    0.22
    Act Density 0.015%

    No Known Activations