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

    Neuronpedia

    INDEX
    Explanations

    phrases that express requirements or conditions for actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    in order to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    brie
    -0.43
    Kaieteur
    -0.42
    хьтан
    -0.39
    emen
    -0.38
    }){
    -0.38
     *++
    -0.38
    .)}
    -0.36
     dip
    -0.36
     uveden
    -0.36
     fVar
    -0.36
    POSITIVE LOGITS
    OGND
    0.52
    ないと
    0.50
    DBNull
    0.50
     noDo
    0.47
    Referències
    0.47
    MockBean
    0.47
    しないと
    0.45
    AndEndTag
    0.44
    SharedDtor
    0.42
     <<<<<<<<<<<<<<
    0.41
    Act Density 0.235%

    No Known Activations