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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating differentiation or distinction from something else

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istr
    -0.15
    blem
    -0.14
     vs
    -0.13
    lio
    -0.13
    ashion
    -0.13
     tw
    -0.13
    acon
    -0.13
     stretched
    -0.13
    eter
    -0.13
    enge
    -0.13
    POSITIVE LOGITS
     Roose
    0.16
    .sat
    0.15
     ///<
    0.15
    SelectedItem
    0.15
     itself
    0.14
    ê·¼
    0.14
    infeld
    0.14
    Hooks
    0.14
    OfSize
    0.13
    _hooks
    0.13
    Act Density 0.030%

    No Known Activations