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

    Neuronpedia

    INDEX
    Explanations

    future-related modal verbs and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     useStyles
    -0.47
    addContainerGap
    -0.45
    ViewImports
    -0.44
     Reſ
    -0.43
    География
    -0.43
    Betrieb
    -0.43
    Pratique
    -0.42
    poptosis
    -0.42
     ſche
    -0.41
    msgTypes
    -0.41
    POSITIVE LOGITS
    zno
    0.40
    zial
    0.37
    岳
    0.37
    PyExc
    0.37
     nødven
    0.36
     CWE
    0.36
     Caspian
    0.35
    京
    0.35
    unately
    0.35
    setdefault
    0.35
    Act Density 0.010%

    No Known Activations