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

    Neuronpedia

    INDEX
    Explanations

    words related to modal verbs and their usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itals
    -0.49
     der
    -0.47
    razza
    -0.45
    itol
    -0.44
    ateľ
    -0.44
     BOY
    -0.42
    tiness
    -0.42
    inez
    -0.40
    WriteTagHelper
    -0.40
    RTEE
    -0.40
    POSITIVE LOGITS
     und
    1.02
     oder
    0.68
     bzw
    0.59
     beziehungs
    0.59
     UND
    0.55
    und
    0.52
     Und
    0.48
     worden
    0.46
     Eſ
    0.42
    Und
    0.42
    Act Density 0.066%

    No Known Activations