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

    Neuronpedia

    INDEX
    Explanations

    references to "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.66
    DockStyle
    -0.63
    setVerticalGroup
    -0.57
    expandindo
    -0.56
     otomatig
    -0.56
    Jîn
    -0.54
    GeoNames
    -0.53
     noDo
    -0.53
     Meksiku
    -0.51
    EndGlobal
    -0.50
    POSITIVE LOGITS
     sole
    0.46
     following
    0.42
     the
    0.38
     contrary
    0.38
     same
    0.36
     slightest
    0.36
    openzeppelin
    0.35
    clerView
    0.35
     amount
    0.35
     opposite
    0.34
    Act Density 0.444%

    No Known Activations